© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    sections of medical or legal documents referring to physical impairments or disabilities, especially those requiring support

    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
    ILayout
    -0.57
    fromnode
    -0.50
     Antic
    -0.50
    irical
    -0.49
     gossi
    -0.48
     gossip
    -0.48
     unethical
    -0.48
     refrigerant
    -0.48
     bross
    -0.46
    GeneratedMessage
    -0.46
    POSITIVE LOGITS
     disability
    1.97
     disabled
    1.81
     Disability
    1.79
     disabilities
    1.70
    Disability
    1.66
     Disabled
    1.62
     wheelchair
    1.60
    disabled
    1.49
     Disabilities
    1.48
    Disabled
    1.47
    Activations Density 1.162%

    No Known Activations