© 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. 18751
    Prev
    Next
    INDEX
    Explanations

    references to ropes and tying mechanisms in contexts involving potential harm or danger

    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
    ########.
    -0.68
     MaterialApp
    -0.68
     logits
    -0.62
     noqa
    -0.61
    GeoNames
    -0.61
     Nuovo
    -0.60
     nugget
    -0.60
     candlestick
    -0.60
     Thine
    -0.59
     eminence
    -0.59
    POSITIVE LOGITS
     rope
    0.86
     ropes
    0.78
     Rope
    0.78
    Rope
    0.75
     strings
    0.67
     corda
    0.67
    dây
    0.65
     Cord
    0.64
    rope
    0.62
     camp
    0.62
    Activations Density 0.050%

    No Known Activations