© 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. 92081
    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
     protoimpl
    -0.61
    oubliez
    -0.59
     Spe
    -0.56
    QMetaType
    -0.55
    providedIn
    -0.55
    IGENCE
    -0.54
    cyklopedia
    -0.54
     Hira
    -0.52
    chargeable
    -0.52
    Spe
    -0.51
    POSITIVE LOGITS
    Geplaatst
    0.84
     disambiguazione
    0.56
    はじめに
    0.54
     JADX
    0.46
     consultato
    0.46
     הגדול
    0.43
     médié
    0.43
    printLine
    0.42
     peix
    0.41
     occidentalis
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.