© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7039
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions or locations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chicago
    -0.81
     NYC
    -0.81
    Chicago
    -0.75
     Seattle
    -0.75
     kasarigan
    -0.73
     Philadel
    -0.72
     Toronto
    -0.68
     NY
    -0.66
    Seattle
    -0.66
     Atlanta
    -0.66
    POSITIVE LOGITS
    ganu
    0.73
    tabria
    0.66
    Anhalt
    0.65
    ptonshire
    0.64
    fordshire
    0.62
    tisgarh
    0.59
    fara
    0.59
    fahan
    0.58
    íba
    0.58
    Pfalz
    0.57
    Activations Density 0.371%

    No Known Activations