© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4446
    Prev
    Next
    INDEX
    Explanations

    references to the Western region of Africa

    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
     south
    -0.84
     north
    -0.83
    south
    -0.73
     South
    -0.72
    South
    -0.67
     North
    -0.62
     SOUTH
    -0.61
    north
    -0.61
     NORTH
    -0.59
    North
    -0.56
    POSITIVE LOGITS
     Western
    3.34
    Western
    3.19
     WESTERN
    2.95
     western
    2.86
    western
    2.67
    WESTERN
    2.66
     wester
    1.95
     occidentale
    1.86
     occidental
    1.84
     occident
    1.72
    Activations Density 0.034%

    No Known Activations