© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3242
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical injuries

    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
    Negative Logits
    //
    -0.47
     فريبيس
    -0.45
     före
    -0.44
     unoccupied
    -0.44
     météo
    -0.44
     unin
    -0.44
     Viss
    -0.43
    forName
    -0.43
    enterOuterAlt
    -0.43
     disease
    -0.42
    POSITIVE LOGITS
     injuries
    1.13
     injury
    1.11
     lacer
    1.10
     wounds
    1.10
     cuts
    1.08
     bruises
    1.05
     contu
    1.04
     Cuts
    1.01
     bruise
    0.98
     Injury
    0.98
    Activations Density 0.219%

    No Known Activations