© 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. 31262
    Prev
    Next
    INDEX
    Explanations

    instances of the word "emphasize" and its variations, indicating a focus on emphasis or importance in the text

    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
     focused
    -0.79
     focus
    -0.73
     direct
    -0.67
     focussed
    -0.67
     Focused
    -0.66
    focused
    -0.66
     deal
    -0.63
    氓
    -0.63
     look
    -0.61
     closest
    -0.61
    POSITIVE LOGITS
     emphasizing
    1.05
     emphasize
    1.03
     emphasized
    1.02
     emphasised
    1.02
    mappedBy
    1.02
     emphasizes
    1.02
     emphasise
    1.01
     emphas
    0.98
    iastes
    0.96
     Emphasis
    0.95
    Activations Density 0.010%

    No Known Activations