© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    medical case studies, especially patient descriptions including age, sex, diagnosis, and treatment

    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
    Either
    -0.96
     Either
    -0.93
     either
    -0.90
     entweder
    -0.88
    either
    -0.88
    或
    -0.80
    RectangleBorder
    -0.79
     or
    -0.79
    거나
    -0.79
     или
    -0.78
    POSITIVE LOGITS
     her
    0.70
     his
    0.70
     she
    0.66
     due
    0.59
    Agrade
    0.58
     hennes
    0.58
     His
    0.56
    шил
    0.56
    his
    0.54
    him
    0.54
    Activations Density 0.401%

    No Known Activations