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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98149
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ParallelGroup
    -0.62
    expandindo
    -0.60
    AnchorStyles
    -0.58
    BeginContext
    -0.55
    rrggbb
    -0.54
    ScopeManager
    -0.54
    ViewImports
    -0.54
    SystemColors
    -0.52
    .*")]
    -0.50
    providedIn
    -0.49
    POSITIVE LOGITS
    recs
    0.57
    hires
    0.55
    chers
    0.54
    estors
    0.54
     vulgaires
    0.54
    Deletes
    0.54
     russes
    0.54
    mbers
    0.52
     exécu
    0.52
    Autoritní
    0.52
    Activations Density 0.019%

    No Known Activations