© 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. 6-RES-MATRYOSHKA-DC
    7. 1131
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially people and places

    oai_token-act-pair · gemini-2.0-flash
    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
     CanadaChoose
    -0.69
    šanai
    -0.65
    ēju
    -0.57
    lau
    -0.54
     Loaf
    -0.54
    Searcher
    -0.54
     Za
    -0.53
    UserScript
    -0.52
     Hag
    -0.50
    SocketAddress
    -0.50
    POSITIVE LOGITS
    arakhand
    0.75
     Indien
    0.73
    anskrit
    0.70
     propOrder
    0.70
     Hindu
    0.69
    లాలు
    0.68
     India
    0.67
     Indians
    0.67
     hindu
    0.67
     Sanskrit
    0.67
    Activations Density 0.913%

    No Known Activations