© 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. 5-CLT-HP
    7. 1955
    Prev
    Next
    INDEX
    Explanations

    medicine or studies

    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
     scaling
    -0.36
    shp
    -0.34
     ship
    -0.34
     Ship
    -0.34
    ങ്ങ
    -0.33
     ko
    -0.33
    гово
    -0.33
    ハリ
    -0.32
     sprzedaż
    -0.32
    образ
    -0.32
    POSITIVE LOGITS
    BufferException
    0.82
    VersionUID
    0.77
    DoubleQuotes
    0.75
    URLException
    0.71
    disposing
    0.71
    oa̍t
    0.69
     يتيمه
    0.68
     MainAxisSize
    0.67
    makeText
    0.67
    GraphicsUnit
    0.67
    Activations Density 0.066%

    No Known Activations