© 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. 20-CLT-HP
    7. 77098
    Prev
    Next
    INDEX
    Explanations

    code and academic writing

    np_max-act-logits · 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
     للمعارف
    -0.71
    gatsby
    -0.71
    queryInterface
    -0.71
     propOrder
    -0.70
    EditorBrowsable
    -0.70
    migrationBuilder
    -0.70
     تضيفلها
    -0.69
    Rhestr
    -0.69
     Roskov
    -0.68
     XCTest
    -0.67
    POSITIVE LOGITS
    bloody
    0.48
     class
    0.46
     miliar
    0.46
    class
    0.46
    TableBody
    0.45
    ighborhood
    0.45
    pantalones
    0.44
     labor
    0.44
    ței
    0.43
     Trading
    0.42
    Activations Density 0.000%

    No Known Activations