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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74303
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    yant
    -0.44
    MessageOf
    -0.44
    anto
    -0.40
    mergeFrom
    -0.38
     Blue
    -0.38
    urlpatterns
    -0.38
    Writ
    -0.38
     c
    -0.38
    شته
    -0.38
    lop
    -0.37
    POSITIVE LOGITS
    Portail
    0.78
    mybatisplus
    0.71
     bezeichneter
    0.69
    RegressionTest
    0.67
    NUMX
    0.66
     Roskov
    0.66
    HtmlAttribute
    0.66
    TintMode
    0.65
    Zeneca
    0.65
    Datuak
    0.65
    Activations Density 0.000%

    No Known Activations