© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    CSS style properties related to font weight

    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
     alluminio
    -0.65
     citoy
    -0.62
     affitto
    -0.60
     trasparente
    -0.59
     déchir
    -0.58
     trouva
    -0.56
     danni
    -0.56
     bianche
    -0.55
     asmen
    -0.55
     coraggio
    -0.54
    POSITIVE LOGITS
     FontWeight
    1.08
    تقاوى
    0.82
     فريبيس
    0.75
    OGND
    0.70
     TextInputType
    0.70
     BorderSide
    0.67
    fontWeight
    0.65
    Personensuche
    0.65
    InputBorder
    0.63
    ContentAsync
    0.63
    Activations Density 0.001%

    No Known Activations