© 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. 1-CLT-HP
    7. 12064
    Prev
    Next
    INDEX
    Explanations

    urbanization, cities

    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
    city
    -0.80
     City
    -0.75
    cities
    -0.73
    City
    -0.71
     CITY
    -0.70
     city
    -0.69
     Cities
    -0.66
    CITY
    -0.60
     cities
    -0.59
    Cities
    -0.58
    POSITIVE LOGITS
     Riks
    0.59
    SuspendLayout
    0.55
    TypedDataSet
    0.55
     ITF
    0.54
    BeginInit
    0.54
     getopt
    0.53
     VSC
    0.53
    DrawerToggle
    0.52
     JpaRepository
    0.52
     Gaulle
    0.50
    Activations Density 0.006%

    No Known Activations