© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1979
    Prev
    Next
    INDEX
    Explanations

    county/city

    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
     County
    -0.98
     City
    -0.90
    County
    -0.85
    City
    -0.82
    ########.
    -0.77
     <>",
    -0.77
     Paglinawan
    -0.76
    NameInMap
    -0.73
    CITY
    -0.69
     city
    -0.67
    POSITIVE LOGITS
    tagHelperRunner
    0.52
     الاطلاع
    0.50
     picioare
    0.50
    нской
    0.49
     Toxicological
    0.48
    setopt
    0.47
     Distinct
    0.46
     Seele
    0.45
     tesoro
    0.45
    ci
    0.45
    Activations Density 1.562%

    No Known Activations