© 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. 1207
    Prev
    Next
    INDEX
    Explanations

    so

    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
     nahilalakip
    -0.94
    abestanden
    -0.94
     pinulongan
    -0.90
    曖昧さ回避
    -0.89
     <=",
    -0.84
    Jeografia
    -0.84
     виправивши
    -0.79
     tartalomajánló
    -0.77
    LEncoder
    -0.77
    انتهای
    -0.77
    POSITIVE LOGITS
    <bos>
    0.88
     that
    0.86
     they
    0.66
     it
    0.61
     to
    0.54
    ↵
    0.54
    '
    0.54
     you
    0.53
     we
    0.49
     why
    0.47
    Activations Density 0.043%

    No Known Activations