© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    references to specific protein domains, particularly the "domain" or "domains" term

    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
     Fitzpatrick
    -0.54
    tiveness
    -0.52
     băng
    -0.50
    пар
    -0.50
     Municipality
    -0.50
    species
    -0.49
     població
    -0.49
     Heine
    -0.49
     PyObject
    -0.48
    drücken
    -0.48
    POSITIVE LOGITS
     domain
    3.52
     Domain
    3.34
    domain
    3.19
    Domain
    3.08
     domains
    3.08
     Domains
    2.88
     DOMAIN
    2.77
    domains
    2.59
    DOMAIN
    2.58
    Domains
    2.58
    Activations Density 0.023%

    No Known Activations