© 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. 3-RES-MATRYOSHKA-DC
    7. 2365
    Prev
    Next
    INDEX
    Explanations

    "United States" (sometimes abbreviated).

    oai_token-act-pair · gemini-2.0-flash
    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
     برانيه
    -1.01
    aarrggbb
    -0.81
    іга
    -0.80
    %");
    -0.73
    migrationBuilder
    -0.69
     onBind
    -0.69
    ficação
    -0.67
     kasarigan
    -0.66
    "]];
    -0.66
    Nazionale
    -0.66
    POSITIVE LOGITS
    S
    0.66
     US
    0.52
     apparente
    0.49
     nicio
    0.48
     county
    0.47
    location
    0.47
    ...
    0.46
    county
    0.46
     ilmo
    0.46
    ospatial
    0.45
    Activations Density 0.055%

    No Known Activations