© 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. 4-CLT-HP
    7. 384
    Prev
    Next
    INDEX
    Explanations

    oral

    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
    interopRequire
    -0.79
    enterOuterAlt
    -0.75
     Réponses
    -0.72
     nahilalakip
    -0.67
    DebuggerStep
    -0.67
    yntaxException
    -0.63
     ExecuteAsync
    -0.63
    ///</
    -0.62
     lèvres
    -0.62
     anledning
    -0.62
    POSITIVE LOGITS
     histories
    0.46
    >//
    0.46
     historians
    0.42
    findById
    0.42
    $_['
    0.41
     writings
    0.41
     reca
    0.40
    ViewChild
    0.40
     historian
    0.39
    rungsseite
    0.37
    Activations Density 0.002%

    No Known Activations