© 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. 4572
    Prev
    Next
    INDEX
    Explanations

    references to the South in different contexts

    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
     western
    -1.27
     eastern
    -1.23
     northern
    -1.20
     northwestern
    -1.20
     occidentale
    -1.17
     northeastern
    -1.15
    west
    -1.13
    western
    -1.12
    eastern
    -1.09
     WESTERN
    -1.08
    POSITIVE LOGITS
     South
    2.56
    South
    2.38
     SOUTH
    1.97
    SOUTH
    1.83
    south
    1.55
     Zuid
    1.31
     south
    1.19
     Sud
    1.12
     Süd
    1.07
    Süd
    1.02
    Activations Density 0.015%

    No Known Activations