© 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. 0-CLT-HP
    7. 38817
    Prev
    Next
    INDEX
    Explanations

    We

    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
    <bos>
    -1.22
     ་་
    -0.75
     Мексичка
    -0.74
    </caption>
    -0.71
    TypedDataSet
    -0.71
     doubtnut
    -0.71
      
    -0.70
     ―――――
    -0.69
     Савезне
    -0.69
    NUMX
    -0.68
    POSITIVE LOGITS
    The
    0.59
    en
    0.59
    A
    0.57
    ing
    0.57
    es
    0.54
    At
    0.53
    To
    0.52
    ic
    0.52
    (
    0.52
    out
    0.50
    Activations Density 4.683%

    No Known Activations