© 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. 32568
    Prev
    Next
    INDEX
    Explanations

    words related to intestinal health and 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
    Negative Logits
     Hirsch
    -0.80
     Mohr
    -0.79
     Hols
    -0.69
    codec
    -0.68
    Failures
    -0.68
    medik
    -0.67
    chedelic
    -0.66
     Lehr
    -0.65
     Acids
    -0.65
    Slf
    -0.65
    POSITIVE LOGITS
    estinal
    0.93
    WriteLiteral
    0.75
    intestinal
    0.71
     GenerationType
    0.68
    }{*}{
    0.67
    ParallelGroup
    0.65
     surla
    0.65
    $~
    0.63
     CIM
    0.62
    Xna
    0.61
    Activations Density 0.002%

    No Known Activations