© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43178
    Prev
    Next
    INDEX
    Explanations

    Dresses and war

    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
     dress
    -0.86
    Dress
    -0.66
     Dress
    -0.64
    OrBuilder
    -0.49
     war
    -0.49
    InteropServices
    -0.48
    dress
    -0.47
    parsedMessage
    -0.44
    supset
    -0.43
    i
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.77
     näky
    0.75
     autorytatywna
    0.73
    :✨
    0.70
    VIAF
    0.70
     ModelExpression
    0.69
     épis
    0.68
     الحره
    0.68
    ViewFeatures
    0.67
    arthed
    0.67
    Activations Density 1.742%

    No Known Activations