© 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. 25416
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bold" and related formatting in 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
    حياته
    -0.82
     Sewell
    -0.80
     Packard
    -0.79
    fucker
    -0.78
     Pram
    -0.77
    Packard
    -0.77
    ClientSize
    -0.74
    opsida
    -0.73
    fjspx
    -0.73
     Aviv
    -0.71
    POSITIVE LOGITS
     Bold
    1.34
    Bold
    1.34
    bold
    1.29
    BOLD
    1.11
     BOLD
    1.11
     bold
    0.96
     boldly
    0.80
     Mould
    0.74
     bolder
    0.68
     Expl
    0.67
    Activations Density 0.004%

    No Known Activations