© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12135
    Prev
    Next
    INDEX
    Explanations

    references to specific methodological details or technical procedures

    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
    Not in Any Lists

    No Comments

    Negative Logits
     specially
    -0.73
     studier
    -0.61
    }{*}{}
    -0.55
     special
    -0.55
     directly
    -0.54
     Even
    -0.54
     специально
    -0.52
    special
    -0.51
     تعت
    -0.50
     Special
    -0.50
    POSITIVE LOGITS
    Specifically
    2.02
     Specifically
    1.96
     Namely
    1.31
     ostavi
    0.82
    帖最后由
    0.75
     Réponses
    0.73
     مشين
    0.72
     nahilalakip
    0.72
     GenerationType
    0.71
     namely
    0.71
    Activations Density 0.002%

    No Known Activations