© 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. 4-CLT-HP
    4. 2866
    Prev
    Next
    INDEX
    Explanations

    code/technical content

    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
    DoubleQuotes
    -0.73
     العنوان
    -0.60
     BoxFit
    -0.60
    Климат
    -0.58
    $_['
    -0.55
     BorderRadius
    -0.54
    LookAnd
    -0.52
    ButterKnife
    -0.50
    setCellValue
    -0.50
    PreferredItem
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.50
    posób
    0.50
    ‌لار
    0.49
    oredCriteria
    0.47
    ğaz
    0.45
     pinulongan
    0.45
    Personensuche
    0.43
     écou
    0.43
    ars
    0.43
    ARS
    0.43
    Activations Density 0.001%

    No Known Activations