© 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. 1-CLT-HP
    7. 9199
    Prev
    Next
    INDEX
    Explanations

    programmed

    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
     UserRepository
    -0.50
     peel
    -0.49
    UserRepository
    -0.47
    벤트
    -0.46
    зыв
    -0.44
    dellín
    -0.43
    izziness
    -0.42
    DebuggerNonUser
    -0.42
    RequestMapping
    -0.42
     naturels
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.90
    MigrationBuilder
    0.82
     utafitiHapana
    0.72
     كومونز
    0.68
    GEBURTSDATUM
    0.66
     للمعارف
    0.66
    ViewFeatures
    0.65
    RenderAtEndOf
    0.63
     pleaſure
    0.62
    @[+][
    0.60
    Activations Density 0.102%

    No Known Activations