© 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. 72634
    Prev
    Next
    INDEX
    Explanations

    Code-like tokens

    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
    MessageTagHelper
    -0.57
     Incident
    -0.54
     pobla
    -0.52
     transitive
    -0.51
    raborty
    -0.49
    addto
    -0.48
     sẻ
    -0.47
    éri
    -0.47
     Writers
    -0.46
     Incidents
    -0.46
    POSITIVE LOGITS
    +#+#
    0.74
    endphp
    0.72
    tagHelperRunner
    0.71
    __(/*!
    0.71
     وتسجيلات
    0.59
    aarrggbb
    0.59
    dymyr
    0.53
    RectangleBorder
    0.53
    MigrationBuilder
    0.51
     سكانية
    0.50
    Activations Density 0.000%

    No Known Activations