© 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. 4-CLT-HP
    7. 4478
    Prev
    Next
    INDEX
    Explanations

    code/unusual formatting

    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
    sheet
    -0.57
    sheets
    -0.55
    ANNES
    -0.52
     luật
    -0.51
    nya
    -0.49
    OrWhiteSpace
    -0.48
    وعة
    -0.48
    setPointSize
    -0.48
    nuts
    -0.47
    scor
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.79
     relâche
    0.65
     esternos
    0.64
     Wiktionnaire
    0.64
     AssemblyProduct
    0.63
    Personensuche
    0.60
     ویکی‌پدی
    0.60
     kautta
    0.60
     testing
    0.58
    iibo
    0.57
    Activations Density 0.001%

    No Known Activations