© 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. 1-CLT-HP
    4. 46307
    Prev
    Next
    INDEX
    Explanations

    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
     city
    -0.85
     City
    -0.76
     CITY
    -0.73
    City
    -0.61
    city
    -0.59
    CITY
    -0.58
     Stadt
    -0.54
     miasto
    -0.51
     ciudad
    -0.51
     город
    -0.51
    POSITIVE LOGITS
    expandindo
    1.06
    msgTypes
    0.76
     везе
    0.73
     CreateTagHelper
    0.73
     OFDb
    0.72
     Biôgrafia
    0.69
    دانشنامهٔ
    0.66
     متعلقه
    0.66
    AddTagHelper
    0.65
    school
    0.64
    Activations Density 0.004%

    No Known Activations