© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 942
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers/licenses

    np_max-act · 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
    TagMode
    -0.81
    aarrggbb
    -0.69
    OptionsMenu
    -0.68
     pinulongan
    -0.67
    setVerticalGroup
    -0.65
    HtmlAttribute
    -0.65
     raiſ
    -0.65
     nonUne
    -0.63
     otomatig
    -0.63
    "?>
    -0.63
    POSITIVE LOGITS
     for
    0.46
    NBT
    0.42
     McCall
    0.42
    HANDLER
    0.41
    so
    0.41
    entown
    0.40
    usercontent
    0.39
    lex
    0.39
    الإنجليزية
    0.39
     until
    0.38
    Activations Density 0.010%

    No Known Activations