© 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. 0-CLT-HP
    7. 94518
    Prev
    Next
    INDEX
    Explanations

    reality

    np_max-act · 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
    ric
    -0.75
    lic
    -0.62
    füh
    -0.58
    ic
    -0.54
    tableFuture
    -0.53
    burnt
    -0.51
    codings
    -0.50
    yoto
    -0.49
    ướng
    -0.48
    ukunfts
    -0.48
    POSITIVE LOGITS
    ViewImports
    0.73
     transfieras
    0.70
    cookieParser
    0.66
     kasarigan
    0.63
     StringField
    0.63
     lenker
    0.62
     invokingState
    0.62
     محفوظة
    0.62
    MigrationBuilder
    0.62
    stylers
    0.61
    Activations Density 0.200%

    No Known Activations