© 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. 72288
    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
     مشين
    -0.73
    ValueStyle
    -0.71
    ItemBackground
    -0.69
     дописавши
    -0.67
    abestanden
    -0.65
    RegressionTest
    -0.63
    ftagPool
    -0.63
     برانيه
    -0.62
    SourceChecksum
    -0.59
    Geografie
    -0.58
    POSITIVE LOGITS
    WSTR
    0.52
    enumii
    0.46
    inka
    0.43
    ʁ
    0.43
    rigues
    0.41
    coo
    0.41
    getMenuInflater
    0.41
     stormed
    0.41
     Droit
    0.41
     swore
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.