© 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. 4-CLT-HP
    7. 540
    Prev
    Next
    INDEX
    Explanations

    in-depth analyses

    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
    EndContext
    -0.81
     HasFactory
    -0.73
    IntoConstraints
    -0.67
    منابع
    -0.67
    SequentialGroup
    -0.64
    LookAnd
    -0.63
    TagMode
    -0.63
    참고
    -0.62
    ontale
    -0.61
    Зноскі
    -0.60
    POSITIVE LOGITS
     deep
    0.65
     diep
    0.56
     into
    0.54
    deep
    0.53
     beneath
    0.47
    PickerController
    0.45
     dipped
    0.44
     DEEP
    0.44
     tief
    0.43
     revealing
    0.43
    Activations Density 0.003%

    No Known Activations