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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1886
    Prev
    Next
    INDEX
    Explanations

    Martin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Martin
    -1.61
    Martin
    -1.52
     MARTIN
    -1.28
     martin
    -1.18
    MARTIN
    -1.12
     sample
    -1.04
     Martín
    -1.03
    sample
    -0.98
    martin
    -0.98
     sampled
    -0.71
    POSITIVE LOGITS
    出版年
    0.96
    XMLSchema
    0.89
     مشين
    0.82
     ModelExpression
    0.78
    protoimpl
    0.75
    awtextra
    0.74
    messageInfo
    0.73
    interopRequire
    0.71
    actéristique
    0.69
    uxxxx
    0.68
    Activations Density 0.110%

    No Known Activations