© 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. 39973
    Prev
    Next
    INDEX
    Explanations

    artefacts

    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
     Round
    -0.77
     старости
    -0.71
    cluye
    -0.64
    Round
    -0.60
     Central
    -0.57
    Central
    -0.55
    sproz
    -0.55
     props
    -0.52
     חיצוניים
    -0.52
    balls
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.77
    astify
    0.72
    DeleteBehavior
    0.71
     mergeFrom
    0.67
    Hentet
    0.66
    AddTagHelper
    0.65
     للمعارف
    0.65
     للاسماء
    0.65
    出版年
    0.63
     intuitively
    0.59
    Activations Density 0.234%

    No Known Activations