© 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. 93771
    Prev
    Next
    INDEX
    Explanations

    emphasize/examines

    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
     المعيارى
    -0.89
     affect
    -0.83
    affect
    -0.81
    ագրություններ
    -0.78
    WriteBarrier
    -0.73
     ویکی‌پدیای
    -0.71
    pulumi
    -0.68
     afect
    -0.68
     wondering
    -0.66
     affecting
    -0.66
    POSITIVE LOGITS
     the
    1.48
     our
    0.90
     your
    0.82
     a
    0.81
     how
    0.79
     what
    0.79
     its
    0.77
     an
    0.74
     everything
    0.71
     those
    0.70
    Activations Density 0.102%

    No Known Activations