© 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. 1-CLT-HP
    7. 9357
    Prev
    Next
    INDEX
    Explanations

    Family

    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
     @"/
    -0.75
    原始内容存档于
    -0.71
    TypedDataSet
    -0.66
     Avalanche
    -0.62
    InjectAttribute
    -0.62
     FetchType
    -0.60
     cellspacing
    -0.59
    Xna
    -0.58
    ContentAlignment
    -0.58
    ATV
    -0.58
    POSITIVE LOGITS
     tecnológicos
    0.42
     químicas
    0.42
     sexuales
    0.41
     proposito
    0.40
     pauvreté
    0.40
    žnost
    0.40
    vč
    0.40
     ciclos
    0.39
     cương
    0.39
    esc
    0.39
    Activations Density 0.038%

    No Known Activations