© 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. 97624
    Prev
    Next
    INDEX
    Explanations

    Found

    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
    ed
    -0.80
    friend
    -0.68
    ized
    -0.67
    ised
    -0.66
    e
    -0.62
    i
    -0.61
     friend
    -0.59
    ists
    -0.57
     Thread
    -0.56
    ist
    -0.54
    POSITIVE LOGITS
    AndEndTag
    0.71
     ویکی‌پدی
    0.68
    SequentialGroup
    0.62
    
    0.61
    __*/
    0.61
    IndentedString
    0.59
     AssemblyCulture
    0.57
    balleur
    0.56
     kasarigan
    0.54
    rrggbb
    0.54
    Activations Density 1.017%

    No Known Activations