© 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. 5-CLT-HP
    7. 97207
    Prev
    Next
    INDEX
    Explanations

    on

    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
    elfde
    -0.57
    itanya
    -0.52
     intptr
    -0.50
    bunya
    -0.47
     Camp
    -0.47
     Италијани
    -0.44
     camp
    -0.44
    yaszt
    -0.43
    sizeCache
    -0.43
    break
    -0.42
    POSITIVE LOGITS
     وتسجيلات
    0.68
     AutoMapper
    0.52
    AutoresizingMask
    0.49
    UnitTesting
    0.49
     Wikispecies
    0.49
    nisses
    0.49
    soka
    0.49
    Coyote
    0.47
    aughey
    0.47
    Automatic
    0.47
    Activations Density 0.001%

    No Known Activations