© 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. 1-CLT-HP
    7. 14284
    Prev
    Next
    INDEX
    Explanations

    active

    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
     active
    -0.90
    Active
    -0.85
     Active
    -0.81
    active
    -0.75
    RenderAtEndOf
    -0.66
    ACTIVE
    -0.63
     ativa
    -0.62
     aktiven
    -0.61
     attiva
    -0.61
     aktive
    -0.60
    POSITIVE LOGITS
    σθαι
    0.69
    MigrationBuilder
    0.63
     myſelf
    0.62
     AppComponent
    0.60
     lenker
    0.57
     ſind
    0.56
     Efq
    0.55
    ^(@)
    0.54
     vane
    0.53
     Ayah
    0.52
    Activations Density 0.018%

    No Known Activations