© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98157
    Prev
    Next
    INDEX
    Explanations

    governmental/geographical divisions

    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
     statewide
    -0.71
     estadual
    -0.67
    県
    -0.59
     state
    -0.56
     राज्य
    -0.56
     Estadual
    -0.55
     county
    -0.54
     State
    -0.52
     Statewide
    -0.51
     regional
    -0.50
    POSITIVE LOGITS
    abestanden
    0.79
    expandindo
    0.78
    </tfoot>
    0.68
    )++;
    0.66
     iſt
    0.65
    APORE
    0.65
    tableFuture
    0.64
    IndentedString
    0.63
     مشارکت‌کنندگان
    0.63
     Airways
    0.59
    Activations Density 0.027%

    No Known Activations