© 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. 94072
    Prev
    Next
    INDEX
    Explanations

    Common English verbs/articles

    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
    Geplaatst
    -0.73
     @"/
    -0.65
     wireType
    -0.65
    HtmlAttribute
    -0.62
     resourceCulture
    -0.62
    WireFormatLite
    -0.59
    InitVars
    -0.59
    __*/
    -0.58
    новниш
    -0.56
     straips
    -0.56
    POSITIVE LOGITS
     represents
    0.66
    rouvez
    0.58
     indicates
    0.57
     provides
    0.57
     reveals
    0.56
    󠁢
    0.56
     includes
    0.55
     describes
    0.54
     reflects
    0.54
     involves
    0.52
    Activations Density 0.122%

    No Known Activations