© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97131
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    __(/*!
    -0.66
     surla
    -0.55
    hloromethane
    -0.54
    PathParam
    -0.53
    emploi
    -0.51
    Geplaatst
    -0.50
    ⓘ
    -0.50
     constituencies
    -0.50
    RenderAtEndOf
    -0.49
    互
    -0.49
    POSITIVE LOGITS
     fermés
    0.71
    orexia
    0.63
    neſs
    0.63
     itſelf
    0.63
     tör
    0.62
     Jefus
    0.61
     fermée
    0.61
    pulseira
    0.59
     normaux
    0.59
    VIRONMENT
    0.59
    Activations Density 0.083%

    No Known Activations