© 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. 360
    Prev
    Next
    INDEX
    Explanations

    references to locations, specifically cities and regions in France

    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
     Monfieur
    -0.68
     purpoſe
    -0.56
    ValueStyle
    -0.55
    ंदीखरीदारी
    -0.52
     Houſe
    -0.51
     pleaſure
    -0.51
     raso
    -0.49
     ſche
    -0.49
     Majefty
    -0.49
     ainfi
    -0.48
    POSITIVE LOGITS
     surla
    0.75
    ########.
    0.75
    homonymie
    0.68
    yntaxException
    0.64
     المعيارى
    0.63
    :+:
    0.52
    Revenir
    0.50
    Naissance
    0.50
     références
    0.48
     mármol
    0.44
    Activations Density 2.402%

    No Known Activations