© 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. 3930
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographic location

    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
    EEA
    -0.60
     Andover
    -0.60
    ngths
    -0.60
     Chennai
    -0.60
     Mumbai
    -0.59
    fortawesome
    -0.58
     Meer
    -0.57
    Bombay
    -0.57
     Duluth
    -0.56
     Bombay
    -0.56
    POSITIVE LOGITS
     Washington
    3.09
    Washington
    2.94
     WASHINGTON
    2.50
     washington
    2.45
    WASHINGTON
    2.08
    washington
    1.95
     Washing
    1.52
     واش
    1.36
     Wash
    1.34
     Ваши
    1.33
    Activations Density 0.005%

    No Known Activations