© 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. 12-RES-MATRYOSHKA-DC
    7. 14163
    Prev
    Next
    INDEX
    Explanations

    references to strokes and stroke-related conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    pellier
    -0.77
     femininas
    -0.73
    elded
    -0.70
     ioutil
    -0.69
    elding
    -0.68
    memberOf
    -0.67
     MCM
    -0.67
    ImageField
    -0.67
    withIdentifier
    -0.65
     namorados
    -0.65
    POSITIVE LOGITS
     stroke
    1.44
    Stroke
    1.43
     Stroke
    1.43
     strokes
    1.41
     Strokes
    1.28
     STRO
    1.20
    strokes
    1.16
    stroke
    1.12
    Stro
    1.08
    STROKE
    1.02
    Activations Density 0.008%

    No Known Activations