© 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. 72995
    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
    UnusedPrivate
    -1.00
     فريبيس
    -0.77
    SourceChecksum
    -0.65
     Waray
    -0.65
     onOptions
    -0.62
    IntoConstraints
    -0.62
    setupUi
    -0.60
    oredCriteria
    -0.59
     lenker
    -0.57
    ">//
    -0.56
    POSITIVE LOGITS
     Multi
    0.56
    Multi
    0.56
    irmer
    0.56
    multi
    0.50
    tiro
    0.50
    meer
    0.50
     Milky
    0.50
     bestaan
    0.49
     multi
    0.49
    PreferredItem
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.