© 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. 0-RES-MATRYOSHKA-DC
    7. 12319
    Prev
    Next
    INDEX
    Explanations

    references to the specific term "dom" or "domain" in various contexts

    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
     DOM
    -1.31
     Domestic
    -1.23
    Domestic
    -1.20
     domestic
    -1.12
     Dom
    -1.09
    Dom
    -0.99
    domestic
    -0.99
     domes
    -0.72
     domestically
    -0.71
     domesti
    -0.71
    POSITIVE LOGITS
    dom
    1.92
    doms
    1.13
     CreateTagHelper
    0.83
     propOrder
    0.66
     nahilalakip
    0.60
    hood
    0.60
    ftagPool
    0.59
     Reap
    0.59
    land
    0.55
    siana
    0.54
    Activations Density 0.001%

    No Known Activations