© 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. 17669
    Prev
    Next
    INDEX
    Explanations

    references to torque in mechanical contexts

    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
     aérea
    -0.94
     propOrder
    -0.88
     idéia
    -0.80
    ::_('
    -0.76
     églises
    -0.75
     deschis
    -0.72
     himo
    -0.71
    >(&
    -0.71
     referenties
    -0.69
     Aérea
    -0.68
    POSITIVE LOGITS
     Torque
    1.54
     torque
    1.52
    Torque
    1.44
    torque
    1.41
     Lohn
    0.73
     toque
    0.70
     Boeh
    0.69
     milling
    0.68
     TOR
    0.67
     tork
    0.67
    Activations Density 0.003%

    No Known Activations