© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2236
    Prev
    Next
    INDEX
    Explanations

    code

    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
     exporting
    -0.94
     export
    -0.86
    Export
    -0.85
     exported
    -0.81
     exports
    -0.81
     Export
    -0.80
    Exports
    -0.73
     exportation
    -0.72
    export
    -0.71
     Exports
    -0.71
    POSITIVE LOGITS
     transfieras
    0.52
     EconPapers
    0.44
     Familienname
    0.43
    contentLoaded
    0.43
    ViewImports
    0.42
    erialized
    0.40
    landaise
    0.40
    messageInfo
    0.40
    usik
    0.39
    ferent
    0.39
    Activations Density 0.005%

    No Known Activations