© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 6570
    Prev
    Next
    INDEX
    Explanations

    HTML class and ID attributes in a coding context

    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
     فريبيس
    -0.93
     pleaſure
    -0.84
     raiſ
    -0.76
     Himo
    -0.75
    λευτα
    -0.74
     greateſt
    -0.74
     دیکھیے
    -0.73
     transfieras
    -0.73
    はじめに
    -0.73
     themſelves
    -0.73
    POSITIVE LOGITS
    Bet
    0.48
    ir
    0.44
     apellidos
    0.43
    )});
    0.43
    üf
    0.42
    >';
    
    0.41
    <h2>
    0.41
     OnInit
    0.41
    ejs
    0.40
    >');
    0.40
    Activations Density 0.012%

    No Known Activations