© 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. 92030
    Prev
    Next
    INDEX
    Explanations

    fix

    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
     fix
    -1.80
     Fix
    -1.33
    fix
    -1.30
     fixes
    -1.23
    Fix
    -1.15
     fixing
    -0.99
     FIX
    -0.94
    fixes
    -0.94
    fixing
    -0.92
     fixation
    -0.88
    POSITIVE LOGITS
    ities
    0.68
    ſelf
    0.68
     iſt
    0.67
     quæ
    0.66
     ſta
    0.65
     itſelf
    0.64
     purpoſe
    0.63
     Eſ
    0.62
    ings
    0.62
     Beſ
    0.61
    Activations Density 0.204%

    No Known Activations