© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1378
    Prev
    Next
    INDEX
    Explanations

    similarities or relatedness between items or concepts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vedno
    -0.64
    äiv
    -0.62
    antaranya
    -0.58
    Different
    -0.57
     Different
    -0.57
    orianCalendar
    -0.57
    iedene
    -0.56
    Wrong
    -0.56
     Wrong
    -0.56
    rungsseite
    -0.53
    POSITIVE LOGITS
     similar
    3.80
    similar
    3.55
    Similar
    3.33
     Similar
    3.31
     SIMILAR
    3.08
     similares
    2.70
     similaire
    2.70
     ähnlichen
    2.48
     ähnliche
    2.42
     semelhante
    2.38
    Activations Density 0.186%

    No Known Activations