© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97570
    Prev
    Next
    INDEX
    Explanations

    Code, links, and names

    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
     للمعارف
    -1.05
    InjectAttribute
    -0.94
    tagHelperRunner
    -0.90
     ExecuteAsync
    -0.80
     pressed
    -0.77
     autorytatywna
    -0.75
     متعلقه
    -0.75
    \{\\
    -0.73
    ">//
    -0.73
     تضيفلها
    -0.71
    POSITIVE LOGITS
    ate
    0.47
    ale
    0.44
    ales
    0.44
    wo
    0.42
    po
    0.42
    ro
    0.41
    set
    0.41
     Caixa
    0.41
     Kanu
    0.40
    als
    0.40
    Activations Density 1.814%

    No Known Activations