© 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. 9197
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shall."

    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
     $_"
    -1.02
     Efq
    -1.02
     itſelf
    -1.01
     myſelf
    -0.95
     Diſ
    -0.94
     estekak
    -0.93
     Wib
    -0.92
    '])){
    -0.91
    -------------</
    -0.91
     raiſ
    -0.91
    POSITIVE LOGITS
     shall
    0.91
    shall
    0.86
    Shall
    0.78
     SHALL
    0.73
     Shall
    0.69
     hath
    0.69
     Hansen
    0.68
    phors
    0.65
    momile
    0.63
     secas
    0.61
    Activations Density 0.005%

    No Known Activations