© 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. 5-CLT-HP
    7. 4979
    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
    <bos>
    -0.65
     createContext
    -0.58
     AssemblyCulture
    -0.45
    forRoot
    -0.45
    例文帳に追加
    -0.44
     grecque
    -0.44
     Franti
    -0.42
     Centre
    -0.42
     chinoise
    -0.42
     centre
    -0.40
    POSITIVE LOGITS
     snippetHide
    0.80
     cherchés
    0.71
     שוליים
    0.71
    featureID
    0.63
    IntoConstraints
    0.61
     Wicidata
    0.61
     MainAxisSize
    0.58
    tvguidetime
    0.57
     ReactDOM
    0.57
     InputDecoration
    0.57
    Activations Density 0.000%

    No Known Activations