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. 12853
    Prev
    Next
    INDEX
    Explanations

    society

    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
     of
    -0.67
     society
    -0.53
     arbete
    -0.49
     مواليد
    -0.49
     société
    -0.48
     held
    -0.47
    ViewFeatures
    -0.45
     незавершена
    -0.45
     volna
    -0.45
     sociétés
    -0.45
    POSITIVE LOGITS
    期刊论文
    0.68
    bootstrapcdn
    0.66
    actionMode
    0.61
    smithy
    0.56
     impra
    0.56
    ranton
    0.55
     Cred
    0.55
    ьаж
    0.54
    inghouse
    0.54
    MemoryWarning
    0.54
    Activations Density 0.151%

    No Known Activations