© 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. 9466
    Prev
    Next
    INDEX
    Explanations

    instances of the word "grab" and its variations

    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
    Negative Logits
     Stillwater
    -0.70
    CardHeader
    -0.69
     Peace
    -0.65
    arkov
    -0.64
     Longfellow
    -0.63
    {{/
    -0.63
    indust
    -0.62
    Peace
    -0.62
    ProductService
    -0.62
     Foote
    -0.60
    POSITIVE LOGITS
     grabbed
    1.08
     grabs
    1.03
     grab
    0.99
     grip
    0.98
     grabbing
    0.98
     grasping
    0.98
     Grab
    0.96
     grasp
    0.94
    Grip
    0.94
    Grab
    0.92
    Activations Density 0.026%

    No Known Activations