© 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. 20-CLT-HP
    7. 74639
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act-logits · 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
    PerformLayout
    -0.84
    RegressionTest
    -0.81
    ंदीखरीदारी
    -0.75
    fillType
    -0.73
     EconPapers
    -0.72
    MemoryWarning
    -0.71
    جوايز
    -0.70
     समीक्षाएं
    -0.68
    لينكات
    -0.68
    DotNetBar
    -0.68
    POSITIVE LOGITS
     change
    1.16
     changes
    0.83
    change
    0.81
     Change
    0.79
    Change
    0.75
     ch
    0.66
     cambio
    0.66
     CHANGE
    0.62
     changement
    0.60
     percent
    0.56
    Activations Density 0.001%

    No Known Activations