© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73690
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    unus
    -0.51
    Educational
    -0.48
    __(/*!
    -0.47
     educational
    -0.47
     Educational
    -0.45
     pener
    -0.45
    RunAsync
    -0.44
    tuto
    -0.43
    +#+
    -0.43
    educational
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.86
    principalColumn
    0.84
    וויק
    0.84
    OGND
    0.84
    UnknownFieldSet
    0.77
     ModelExpression
    0.72
     TextAppearance
    0.68
    ंदीखरीदारी
    0.64
     resourceCulture
    0.63
    addCriterion
    0.62
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.