© 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. 1-CLT-HP
    7. 11605
    Prev
    Next
    INDEX
    Explanations

    part

    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
     CreateTagHelper
    -0.71
     InputDecoration
    -0.66
    IndentedString
    -0.64
     disambiguazione
    -0.61
     صوتيه
    -0.61
     contextLoads
    -0.58
     ModelExpression
    -0.57
     समीक्षक
    -0.56
    EnableWeb
    -0.56
     pierdas
    -0.56
    POSITIVE LOGITS
     Mawr
    0.52
    //
    0.49
    twimg
    0.48
    ling
    0.47
     pú
    0.47
     upland
    0.47
    nson
    0.47
     Elk
    0.47
     roe
    0.47
     Trich
    0.46
    Activations Density 0.003%

    No Known Activations