© 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. 2-RES-MATRYOSHKA-DC
    7. 6036
    Prev
    Next
    INDEX
    Explanations

    references to cancer or oncological topics

    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
     AssemblyCulture
    -1.12
     виправивши
    -0.96
    findpost
    -0.90
     nahilalakip
    -0.88
     समीक्षक
    -0.83
    ValueStyle
    -0.77
    DoubleQuotes
    -0.76
     للمعارف
    -0.73
    protoimpl
    -0.72
    hoeddwyd
    -0.71
    POSITIVE LOGITS
     onCancelled
    0.54
    EDS
    0.46
    pacs
    0.43
     Анато
    0.43
     häls
    0.43
     frigo
    0.43
     Moreno
    0.42
    öch
    0.42
    اض
    0.41
    ∅
    0.41
    Activations Density 0.010%

    No Known Activations