© 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. 20606
    Prev
    Next
    INDEX
    Explanations

    references to Texas legal cases or statutes

    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
    rungsseite
    -0.77
    queryInterface
    -0.71
    reactstrap
    -0.67
     kaynağından
    -0.64
    addGap
    -0.63
    HasAnnotation
    -0.62
     propOrder
    -0.62
     continúas
    -0.61
    uxxxx
    -0.57
     sanitaires
    -0.57
    POSITIVE LOGITS
     ſche
    0.79
     $_"
    0.78
    出版年
    0.77
     purpoſe
    0.77
     Anſ
    0.75
     $_(
    0.72
     doubtnut
    0.69
    "?>
    0.69
     tfsi
    0.68
     Diſ
    0.68
    Activations Density 0.000%

    No Known Activations