© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13887
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, specifically related to Sweden

    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
     '\\;'
    -0.86
    fillType
    -0.81
    findpost
    -0.79
     Waray
    -0.75
     Cæsar
    -0.71
     Shakspeare
    -0.69
    expandindo
    -0.68
     Toussaint
    -0.66
    Personensuche
    -0.66
     Inuit
    -0.66
    POSITIVE LOGITS
     Sweden
    2.16
     Swedish
    1.93
    Sweden
    1.93
    Swedish
    1.76
     swedish
    1.35
     Schweden
    1.28
     Sverige
    1.23
     sweden
    1.23
     Suecia
    1.23
     Swedes
    1.18
    Activations Density 0.003%

    No Known Activations