© 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. 20-CLT-HP
    7. 72778
    Prev
    Next
    INDEX
    Explanations

    programming code or documentation

    np_max-act-logits · 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
    httphttps
    -0.60
    –
    -0.56
    XmlAccessType
    -0.52
     BoxDecoration
    -0.52
    ListItemIcon
    -0.51
     initComponents
    -0.50
    migrationBuilder
    -0.49
     CWE
    -0.49
     Felicity
    -0.47
    addCriterion
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    DoubleQuotes
    0.72
    }{*}{}
    0.63
    InputBorder
    0.60
    EndInit
    0.56
    endmodule
    0.55
     Wikispecies
    0.55
    ChildScrollView
    0.52
    >{@
    0.52
    izr
    0.51
    Activations Density 0.003%

    No Known Activations