© 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. 1890
    Prev
    Next
    INDEX
    Explanations

    language in medical papers

    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
     diabetes
    -0.48
     cancer
    -0.48
     blood
    -0.48
    AsyncResult
    -0.48
     bad
    -0.46
     câncer
    -0.45
    bad
    -0.45
    Nuorodos
    -0.44
     levels
    -0.44
    orrhea
    -0.44
    POSITIVE LOGITS
     rare
    1.15
    Rare
    1.14
     rarest
    1.10
     rarity
    1.09
     Rare
    1.09
     rarer
    1.04
    rare
    1.03
     Rarely
    0.94
     uncommon
    0.94
     متعلقه
    0.88
    Activations Density 0.983%

    No Known Activations