© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93650
    Prev
    Next
    INDEX
    Explanations

    alternatives, comparisons

    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
     nor
    -1.04
     Nor
    -0.90
    Nor
    -0.77
    nor
    -0.73
     tampoco
    -0.67
    而是
    -0.67
     Tampoco
    -0.59
     Nevertheless
    -0.56
     configureStore
    -0.56
     NOR
    -0.55
    POSITIVE LOGITS
    सन्दर्भ
    0.65
    MigrationBuilder
    0.65
     pleaſure
    0.60
     Monfieur
    0.57
    ỡng
    0.56
    المناصب
    0.56
    GraphicsUnit
    0.56
    ########.
    0.54
     ſta
    0.53
    IsContent
    0.52
    Activations Density 0.045%

    No Known Activations