© 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. 4-CLT-HP
    7. 3416
    Prev
    Next
    INDEX
    Explanations

    code or structured documents

    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
     whor
    -0.36
    haikusbot
    -0.36
    Electron
    -0.35
     comming
    -0.35
    Pty
    -0.34
     skry
    -0.34
     elector
    -0.34
    кономі
    -0.34
     Pacific
    -0.33
     PyQt
    -0.33
    POSITIVE LOGITS
     AssemblyCulture
    0.70
    MessageOf
    0.66
     étoient
    0.65
    PerformLayout
    0.63
     financière
    0.63
     avoient
    0.63
     résister
    0.63
     élastique
    0.63
    værende
    0.62
    IsMutable
    0.60
    Activations Density 0.000%

    No Known Activations