© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    7

    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
     sherds
    -0.72
     rafters
    -0.54
    quakes
    -0.54
     classmate
    -0.54
     whistles
    -0.53
     sightings
    -0.53
     ſever
    -0.53
    LookAnd
    -0.52
    脚注の使い方
    -0.52
    出版年
    -0.52
    POSITIVE LOGITS
    ếng
    0.58
     Full
    0.58
    withIdentifier
    0.56
     Mass
    0.54
    CppMethod
    0.53
    contentPadding
    0.51
     Gesch
    0.50
     General
    0.50
    wapV
    0.50
    eclared
    0.50
    Activations Density 0.001%

    No Known Activations