© 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. 1-CLT-HP
    7. 521
    Prev
    Next
    INDEX
    Explanations

    children

    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>
    -0.72
     $\
    -0.44
    Slf
    -0.44
    \
    -0.41
     points
    -0.40
    ↵
    -0.39
    гат
    -0.39
     patterns
    -0.36
     in
    -0.36
    (
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.82
    XtraEditors
    0.72
    romyalgia
    0.70
    ValueStyle
    0.69
    IonicModule
    0.69
    taxia
    0.68
    toBeTruthy
    0.67
     Bioaccumulative
    0.66
    reportWebVitals
    0.63
     Vikipedi
    0.63
    Activations Density 0.050%

    No Known Activations