© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2058
    Prev
    Next
    INDEX
    Explanations

    leadership/politics

    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
    President
    -0.50
    sizePolicy
    -0.49
     cellulare
    -0.48
     to
    -0.46
     évêque
    -0.46
     isolado
    -0.46
     către
    -0.46
     fidèle
    -0.44
     bienven
    -0.44
     efficacement
    -0.44
    POSITIVE LOGITS
     coalition
    0.61
     consortium
    0.60
     Roskov
    0.58
     experiment
    0.56
    RegistryLite
    0.56
    IBOutlet
    0.56
    новниш
    0.56
     virtual
    0.56
     crusade
    0.56
     commission
    0.54
    Activations Density 0.002%

    No Known Activations