© 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. 4989
    Prev
    Next
    INDEX
    Explanations

    Reference

    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
    featureID
    -0.76
    SequentialGroup
    -0.75
    ArgsConstructor
    -0.68
    sizeCache
    -0.67
    ://$
    -0.66
    yntaxException
    -0.61
     disambiguazione
    -0.61
    Contours
    -0.61
    RectangleBorder
    -0.60
    막
    -0.60
    POSITIVE LOGITS
     تكبرها
    0.47
     English
    0.42
     turno
    0.41
     jdbcTemplate
    0.39
    ranslated
    0.39
     gehört
    0.38
     hoort
    0.37
    databind
    0.36
     completeness
    0.36
     Duane
    0.35
    Activations Density 0.003%

    No Known Activations