© 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. 71923
    Prev
    Next
    INDEX
    Explanations

    Code/Errors

    np_max-act-logits · gemini-2.0-flash
    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
     autorytatywna
    -0.70
    LookAnd
    -0.64
     CommonModule
    -0.64
     useDispatch
    -0.60
    MigrationBuilder
    -0.57
    sikal
    -0.57
    ölkerung
    -0.57
    awaiter
    -0.56
     hikers
    -0.56
     Muses
    -0.56
    POSITIVE LOGITS
     Waray
    0.47
    AutoresizingMask
    0.47
     cor
    0.47
     Fay
    0.45
    WebControls
    0.45
    galo
    0.43
     المعيارى
    0.42
    Geplaatst
    0.42
    greja
    0.41
    gar
    0.40
    Activations Density 0.002%

    No Known Activations