© 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. 6670
    Prev
    Next
    INDEX
    Explanations

    instances of formatting and styling elements 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
    principalTable
    -1.18
     tartalomajánló
    -1.03
     مشين
    -0.96
     חיצוניים
    -0.92
    :✨
    -0.86
     nahilalakip
    -0.86
     lenker
    -0.85
     Roskov
    -0.85
    TagMode
    -0.84
     propOrder
    -0.84
    POSITIVE LOGITS
    TASKS
    0.44
     readline
    0.43
     advis
    0.40
    wasi
    0.38
    КУ
    0.38
     Públicas
    0.38
     advisory
    0.37
     breakfasts
    0.37
    readline
    0.36
     Shaun
    0.36
    Activations Density 0.558%

    No Known Activations