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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    Names, places

    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
     bogotá
    -0.68
     Asunción
    -0.66
     Mejía
    -0.65
     Almería
    -0.64
     Guimarães
    -0.62
     Ceará
    -0.57
     Guayaquil
    -0.56
     Curitiba
    -0.56
     Afonso
    -0.56
     Jardim
    -0.56
    POSITIVE LOGITS
     de
    0.77
     del
    0.71
     Arri
    0.56
     Carried
    0.56
     y
    0.55
     Grande
    0.53
    IBarButtonItem
    0.53
     Ber
    0.52
     Amar
    0.51
     Caro
    0.51
    Activations Density 0.832%

    No Known Activations