© 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. 45401
    Prev
    Next
    INDEX
    Explanations

    cause

    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
    ing
    -0.66
    scheme
    -0.56
    amental
    -0.54
    ments
    -0.52
    ruff
    -0.49
    nements
    -0.48
    complexContent
    -0.48
     виправивши
    -0.48
     صوتيه
    -0.48
    lyk
    -0.48
    POSITIVE LOGITS
     ExecuteAsync
    0.72
    πάρχ
    0.65
     مشارکت‌کنندگان
    0.57
     poches
    0.56
    //</
    0.55
    IsContent
    0.55
     pockets
    0.54
    invokeLater
    0.54
     terakhir
    0.54
    ollectionView
    0.53
    Activations Density 1.306%

    No Known Activations