© 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. 17136
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to page styling and color settings

    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
     nahilalakip
    -0.73
    MigrationBuilder
    -0.66
    رشف
    -0.65
    GraphicsUnit
    -0.65
    ########.
    -0.63
     елның
    -0.61
     المعيارى
    -0.60
    ToAction
    -0.60
     الرياضيه
    -0.60
     ffilmiau
    -0.59
    POSITIVE LOGITS
     bgcolor
    1.90
    bgcolor
    1.34
     Viol
    0.63
     Lari
    0.62
     Sora
    0.61
    COLOR
    0.61
    BackColor
    0.59
     Jor
    0.59
     paj
    0.58
     viol
    0.58
    Activations Density 0.003%

    No Known Activations