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. 22-CLT-HP
    4. 74482
    Prev
    Next
    INDEX
    Explanations

    Science and academic writing

    np_max-act-logits · 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
    +#+#
    -0.85
    tvguidetime
    -0.85
    Билгалдахарш
    -0.78
    expandindo
    -0.78
    webElementXpaths
    -0.78
     disambiguazione
    -0.75
    Искәрмәләр
    -0.73
    SharedDtor
    -0.71
    MemoryWarning
    -0.70
    mybatisplus
    -0.70
    POSITIVE LOGITS
     Sons
    0.41
     shen
    0.40
    riba
    0.40
    ouac
    0.40
     parade
    0.39
     geography
    0.39
    bane
    0.37
     }).
    0.37
     society
    0.37
    Braun
    0.37
    Activations Density 0.003%

    No Known Activations