© 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. 20-CLT-HP
    7. 76199
    Prev
    Next
    INDEX
    Explanations

    affecting factors

    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
     ویکی‌پدی
    -0.82
    +#+#
    -0.77
    TestingModule
    -0.71
    İstinadlar
    -0.70
    ftagPool
    -0.70
     Signalez
    -0.69
    MigrationBuilder
    -0.68
    EndInit
    -0.66
     näm
    -0.66
     سكانية
    -0.62
    POSITIVE LOGITS
     affecting
    0.49
     internal
    0.47
     geografic
    0.47
    parametric
    0.45
     associated
    0.45
    internal
    0.43
     fa
    0.42
    fic
    0.42
     parametric
    0.42
    faf
    0.41
    Activations Density 0.001%

    No Known Activations