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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91948
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
    出版年
    -0.64
    theless
    -0.61
    etheless
    -0.58
    PERATURE
    -0.57
     Efq
    -0.57
    esterday
    -0.57
    INDA
    -0.56
    iteness
    -0.56
    tersebut
    -0.55
     stället
    -0.55
    POSITIVE LOGITS
    تقاوى
    0.73
     ostavi
    0.47
    endregion
    0.47
    LookAnd
    0.46
     for
    0.45
     beginnetje
    0.45
    fels
    0.45
     ویکی‌پدیا
    0.44
    templateUrl
    0.44
     DataTypes
    0.44
    Activations Density 0.122%

    No Known Activations