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. 73986
    Prev
    Next
    INDEX
    Explanations

    Technical/code snippets

    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
     AspNetCore
    -0.71
    aarrggbb
    -0.66
     otomatig
    -0.57
    ::$_
    -0.54
    RegistryLite
    -0.54
    XtraEditors
    -0.51
    onOptions
    -0.49
    culosis
    -0.48
    ///</
    -0.48
     <>",
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.70
    twimg
    0.63
     have
    0.57
     be
    0.56
    мені
    0.55
    řízení
    0.54
    <()>
    0.53
    hap
    0.52
    ilitation
    0.52
    nti
    0.52
    Activations Density 0.000%

    No Known Activations