© 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. 22-RES-MATRYOSHKA-DC
    7. 2792
    Prev
    Next
    INDEX
    Explanations

    terminology and context related to oxygen and hypoxia, especially arterial oxygen levels and clinical situations

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comstock
    -0.57
     Lessing
    -0.46
    charCodeAt
    -0.46
    XDECREF
    -0.45
     Orrell
    -0.45
     Grease
    -0.44
    pageId
    -0.43
     dishwasher
    -0.43
    ürze
    -0.43
     Lampung
    -0.43
    POSITIVE LOGITS
     oxygen
    1.45
     Oxygen
    1.30
    Oxygen
    1.27
    oxygen
    1.23
     hypoxia
    1.12
     Sauerstoff
    0.98
     oxigen
    0.91
     oxígeno
    0.91
    氧
    0.91
     oxy
    0.85
    Activations Density 0.220%

    No Known Activations