© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6232
    Prev
    Next
    INDEX
    Explanations

    geographic locations

    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
    Negative Logits
     CommonModule
    -0.77
    ISupport
    -0.69
     дописавши
    -0.66
     Jefus
    -0.65
    CodeAttribute
    -0.64
     uſed
    -0.64
    providedIn
    -0.63
     itſelf
    -0.62
     purpoſe
    -0.60
     whoſe
    -0.60
    POSITIVE LOGITS
     patterns
    0.62
     distributions
    0.60
     carbon
    0.54
     balances
    0.52
     distribution
    0.49
     amounts
    0.48
     cycles
    0.47
    -
    0.45
     climate
    0.45
     die
    0.45
    Activations Density 0.000%

    No Known Activations