© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging techniques, biological markers, and laboratory procedures

    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
    unmodifiable
    -0.58
    getMenuInflater
    -0.54
    胱
    -0.53
    nemer
    -0.52
    osk
    -0.52
     spē
    -0.50
    BEAT
    -0.49
    送り
    -0.48
     jury
    -0.48
     beat
    -0.47
    POSITIVE LOGITS
    DMETHOD
    0.88
    eclampsia
    0.75
    RegisterType
    0.73
    SESSION
    0.71
    addons
    0.71
    StringProperty
    0.71
    setViewportView
    0.70
    cloak
    0.68
    allus
    0.65
     monolithic
    0.65
    Activations Density 0.097%

    No Known Activations