© 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. 41439
    Prev
    Next
    INDEX
    Explanations

    File conversions and disaster relief

    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
    DoubleQuotes
    -0.90
     BorderRadius
    -0.81
     NSCoder
    -0.79
     autorytatywna
    -0.76
     ddelweddau
    -0.75
     تضيفلها
    -0.74
    HandlerContext
    -0.71
     ✭✭
    -0.71
     nahilalakip
    -0.71
     يتيمه
    -0.69
    POSITIVE LOGITS
     the
    0.52
     Bus
    0.50
     a
    0.48
     of
    0.47
    bus
    0.45
    \}^{
    0.44
     Her
    0.44
    mp
    0.44
     S
    0.43
     wide
    0.43
    Activations Density 0.290%

    No Known Activations