© 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. 26942
    Prev
    Next
    INDEX
    Explanations

    references to pigs and related terminology

    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
     estekak
    -1.02
    ReusableCell
    -0.79
     EconPapers
    -0.78
    StoryboardSegue
    -0.76
     PES
    -0.74
     intptr
    -0.74
    setLayout
    -0.74
     Roca
    -0.74
    談社
    -0.73
     (_.
    -0.73
    POSITIVE LOGITS
     pigs
    1.75
     Pig
    1.73
     pig
    1.69
    Pig
    1.61
    pig
    1.56
     Pigs
    1.50
     PIG
    1.45
     pork
    1.26
     Pork
    1.14
     swine
    1.11
    Activations Density 0.011%

    No Known Activations