© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    ScopeManager
    -0.79
    parsedMessage
    -0.70
    makeConstraints
    -0.68
     متعلقه
    -0.65
    ThroughAttribute
    -0.64
     juzg
    -0.64
    tagHelperRunner
    -0.62
     sumpay
    -0.61
    ftagPool
    -0.60
    ResumeLayout
    -0.58
    POSITIVE LOGITS
    Przypisy
    0.53
     local
    0.51
    自然是
    0.47
    当然是
    0.47
    lait
    0.47
     astore
    0.47
     ισ
    0.46
    (
    0.46
    qtype
    0.46
    ;
    0.46
    Activations Density 0.009%

    No Known Activations