© 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. 6124
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations and associated names

    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
     Provo
    -0.75
    Kew
    -0.68
    provo
    -0.65
     Giovan
    -0.63
     Kew
    -0.62
     Vau
    -0.61
    ặp
    -0.61
    enterOuterAlt
    -0.59
     Gew
    -0.59
     Turk
    -0.59
    POSITIVE LOGITS
     DETROIT
    0.95
    Detroit
    0.87
     Toledo
    0.87
     Detroit
    0.85
    Toledo
    0.85
     poland
    0.83
    Poland
    0.82
     Biel
    0.79
     Belt
    0.79
     adhé
    0.79
    Activations Density 1.564%

    No Known Activations