Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12882
    Prev
    Next
    INDEX
    Explanations

    cliff

    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
     espirituales
    -0.66
     vérit
    -0.65
     supérieures
    -0.63
     vœux
    -0.63
     prisonniers
    -0.63
     religieuses
    -0.61
     réfugi
    -0.60
     chré
    -0.59
     juger
    -0.59
     afectadas
    -0.59
    POSITIVE LOGITS
    riwal
    0.61
    IsContent
    0.59
    Cyfeiriadau
    0.55
    protoimpl
    0.54
    mergeFrom
    0.52
    lunda
    0.52
    Демографія
    0.50
     eventdata
    0.50
     Propriet
    0.50
     ②
    0.50
    Activations Density 0.023%

    No Known Activations