© 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. 44048
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    RegressionTest
    -0.93
    expandindo
    -0.80
     autorytatywna
    -0.79
    Portail
    -0.75
    aarrggbb
    -0.72
    rungsseite
    -0.71
     disambiguazione
    -0.71
    ↵↵
    -0.71
     ModelExpression
    -0.71
    AccessorTable
    -0.70
    POSITIVE LOGITS
    -
    0.73
    by
    0.65
    \
    0.60
    (
    0.60
    and
    0.59
    I
    0.58
    •
    0.58
    from
    0.57
    </h1>
    0.57
    <b>
    0.56
    Activations Density 0.083%

    No Known Activations