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. 74275
    Prev
    Next
    INDEX
    Explanations

    Technical/code context

    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
     nights
    -0.66
     Nights
    -0.63
     evenings
    -0.57
     Paglinawan
    -0.54
    RUnlock
    -0.54
     quarters
    -0.54
    Nights
    -0.54
    quarters
    -0.52
    bootstrapcdn
    -0.52
     afternoons
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    0.80
    AndEndTag
    0.73
    Демографія
    0.61
    HtmlAttribute
    0.59
     виправивши
    0.55
     AssemblyTitle
    0.53
     незавершена
    0.52
    TypedDataSet
    0.51
     يتيمه
    0.49
    other
    0.47
    Activations Density 0.005%

    No Known Activations