© 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. 786
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
     any
    -0.69
     ANY
    -0.56
     cualquier
    -0.56
     if
    -0.54
     Any
    -0.52
     Walkover
    -0.52
     qualquer
    -0.50
     cualquiera
    -0.50
     potest
    -0.50
     bør
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
    новниш
    0.66
     saites
    0.63
     صوتيه
    0.62
     Wikispecies
    0.62
     thiệu
    0.62
     jspb
    0.59
    帖最后由
    0.59
    FormTagHelper
    0.57
     esternos
    0.57
    Activations Density 0.006%

    No Known Activations