© 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. 93511
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     more
    -0.60
     ſuch
    -0.60
     other
    -0.58
     two
    -0.57
     additional
    -0.54
     small
    -0.54
     ſeveral
    -0.54
     different
    -0.52
     leaſt
    -0.52
     ſaid
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.73
     genoux
    0.72
     المعيارى
    0.68
     estimés
    0.65
    '
    0.63
     vœux
    0.60
    ThroughAttribute
    0.60
     blessés
    0.60
     épaules
    0.59
    InSection
    0.58
    Activations Density 0.310%

    No Known Activations