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. 74317
    Prev
    Next
    INDEX
    Explanations

    Formal and technical text

    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
    ########.
    -0.93
     jScrollPane
    -0.83
    tagHelperRunner
    -0.73
    новниш
    -0.73
    EndInit
    -0.72
    TagHelpers
    -0.71
     مرئيه
    -0.71
    protoimpl
    -0.71
    Aiheesta
    -0.70
    styleType
    -0.70
    POSITIVE LOGITS
     the
    0.52
     Congress
    0.47
     brancas
    0.41
     nő
    0.40
     set
    0.40
     allo
    0.39
    stackrel
    0.38
     Cambridge
    0.38
     uitgebre
    0.38
     kanyang
    0.38
    Activations Density 0.000%

    No Known Activations