© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 416
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations and geographic data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    aarrggbb
    -0.46
    findpost
    -0.41
     představ
    -0.41
     verificación
    -0.41
     distanciation
    -0.40
     determination
    -0.40
     determinación
    -0.40
     Toilette
    -0.40
    Paraguay
    -0.39
     Merdeka
    -0.39
    POSITIVE LOGITS
     South
    0.83
     North
    0.83
     southern
    0.76
     Northern
    0.74
     Southern
    0.73
     northern
    0.73
     cities
    0.68
     south
    0.67
    southern
    0.66
    North
    0.65
    Activations Density 3.558%

    No Known Activations