© 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. 72132
    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
    featureID
    -0.78
     beginnetje
    -0.77
    MigrationBuilder
    -0.69
    Autoritní
    -0.66
    StreetMap
    -0.65
     PeEnEo
    -0.63
     AssemblyCulture
    -0.63
    Hentet
    -0.62
    webElementXpaths
    -0.62
    LookAnd
    -0.62
    POSITIVE LOGITS
    직
    0.40
     useDispatch
    0.39
     aç
    0.37
    ijnlijk
    0.36
    newArrayList
    0.36
    toHave
    0.36
     carmen
    0.35
     spoiled
    0.35
    osamente
    0.35
    //
    0.34
    Activations Density 0.000%

    No Known Activations