© 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. 39965
    Prev
    Next
    INDEX
    Explanations

    people

    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
     militaires
    -0.73
     huiles
    -0.71
     financières
    -0.69
     financieros
    -0.68
     sauvages
    -0.68
     communs
    -0.68
     industriels
    -0.67
     temporales
    -0.67
     religieuses
    -0.66
     démocr
    -0.66
    POSITIVE LOGITS
    <bos>
    0.66
     '\\;'
    0.65
     متعلقه
    0.63
    ⓧ
    0.62
     Normdatei
    0.61
    caris
    0.57
     informée
    0.57
    ^(@)
    0.56
     חיצוניים
    0.56
    RegressionTest
    0.56
    Activations Density 0.434%

    No Known Activations