© 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. 418
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and natural features

    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
     SYDNEY
    -0.49
     København
    -0.48
     LONDON
    -0.48
     Wrocław
    -0.47
     TORONTO
    -0.47
     torture
    -0.47
     Jakarta
    -0.46
    InitVars
    -0.46
     fhew
    -0.46
     zł
    -0.45
    POSITIVE LOGITS
     east
    0.56
    RectangleBorder
    0.56
     north
    0.54
     south
    0.52
     west
    0.52
     inland
    0.52
     eastern
    0.50
     towns
    0.49
     county
    0.48
     rural
    0.48
    Activations Density 2.471%

    No Known Activations