© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90786
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     peines
    -0.48
    dry
    -0.41
     forno
    -0.41
     commerciales
    -0.40
     of
    -0.40
    click
    -0.40
     Elias
    -0.39
    redux
    -0.39
     Código
    -0.39
     ب
    -0.38
    POSITIVE LOGITS
     itſelf
    1.00
    ised
    0.99
     AssemblyCulture
    0.95
    AndEndTag
    0.95
    ities
    0.92
     propOrder
    0.92
    ⓧ
    0.87
     ModelExpression
    0.84
    
    0.84
    kháu
    0.83
    Activations Density 0.290%

    No Known Activations