© 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. 0-RES-MATRYOSHKA-DC
    7. 10432
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical quantities or proportions

    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
     (
    -1.04
     by
    -1.00
     from
    -0.99
    :
    -0.99
     in
    -0.97
    ,
    -0.97
     S
    -0.96
     I
    -0.96
     for
    -0.94
     a
    -0.93
    POSITIVE LOGITS
     itſelf
    1.86
     Theſe
    1.80
     myſelf
    1.79
     Houſe
    1.73
     Forumite
    1.69
     Anſ
    1.63
     Мексичка
    1.62
     Diſ
    1.62
     ſtate
    1.62
     greateſt
    1.61
    Activations Density 0.794%

    No Known Activations