Embedding Projector
A TensorFlow tool that reduces embeddings — data such as words represented as vectors of hundreds of dimensions — down to two or three dimensions you can look at. It opens on 10,000 Word2Vec words in 200 dimensions, and picking one word lists its nearest neighbours. You come away seeing directly that words with related meanings sit close together in the space.
How to try it
Type a word in the search box on the right or click a point, and its nearest neighbours appear with their distances; you can switch the distance measure between cosine and Euclidean. The UMAP, T-SNE and PCA tabs at the lower left change the dimensionality reduction so you can compare how the same data rearranges itself, and 'Load' lets you upload your own TSV of vectors. The interface is English only and it renders 10,000 points in 3D, so a desktop browser is recommended.