© 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. 3531
    Prev
    Next
    INDEX
    Explanations

    references to biological states or conditions

    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
    setVerticalGroup
    -0.80
    NamedQueries
    -0.78
    AddTagHelper
    -0.78
    AsUp
    -0.71
     صوتيه
    -0.71
    Демографія
    -0.70
    UnusedPrivate
    -0.68
    queryInterface
    -0.63
    )");
    -0.62
    Vidite
    -0.61
    POSITIVE LOGITS
     religieuses
    0.66
     européennes
    0.61
     étrangères
    0.60
     européens
    0.59
     extérieures
    0.58
     publiques
    0.56
     humaines
    0.54
     ước
    0.54
     françaises
    0.53
     supérieures
    0.53
    Activations Density 2.520%

    No Known Activations