© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3468
    Prev
    Next
    INDEX
    Explanations

    references to local government officials, specifically "mayor."

    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
    +#+#
    -0.62
     sta
    -0.59
    isLoaded
    -0.58
    Brien
    -0.57
    irmish
    -0.55
    humidité
    -0.55
     ziren
    -0.54
    )$\\
    -0.54
    "]=
    -0.54
     agences
    -0.54
    POSITIVE LOGITS
     mayor
    2.92
     Mayor
    2.92
    Mayor
    2.80
     MAYOR
    2.67
    mayor
    2.45
     mayors
    2.34
     mayoral
    1.87
     sindaco
    1.55
     maire
    1.36
     alcalde
    1.34
    Activations Density 0.020%

    No Known Activations