© 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. 0-CLT-HP
    7. 41513
    Prev
    Next
    INDEX
    Explanations

    Latex/code

    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
    ArrowToggle
    -0.81
    RenderAtEndOf
    -0.78
     étoient
    -0.77
     avoient
    -0.77
     ویکی‌پدیای
    -0.76
    actéristique
    -0.72
     betweenstory
    -0.71
     abstrait
    -0.70
    tvguidetime
    -0.70
     abstrato
    -0.70
    POSITIVE LOGITS
    AlterField
    0.44
     ever
    0.44
    '
    0.43
     kon
    0.43
    DeleteCommand
    0.43
     Kon
    0.43
    рення
    0.42
    stro
    0.42
     electronics
    0.41
     теле
    0.41
    Activations Density 0.087%

    No Known Activations