© 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. 5-CLT-HP
    7. 98288
    Prev
    Next
    INDEX
    Explanations

    route

    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
     QtWidgets
    -0.45
     placé
    -0.42
     écoute
    -0.41
     goû
    -0.40
    servable
    -0.40
    渍
    -0.40
     souri
    -0.39
     placés
    -0.39
     détruit
    -0.39
     écoulé
    -0.38
    POSITIVE LOGITS
     selection
    0.85
    +#+#
    0.78
     CreateTagHelper
    0.76
     ModelExpression
    0.75
     choice
    0.75
    finding
    0.73
    InputBorder
    0.73
     calculation
    0.69
    richTextPanel
    0.69
     recommendation
    0.68
    Activations Density 0.002%

    No Known Activations