© 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. 17724
    Prev
    Next
    INDEX
    Explanations

    references to legal circuits or court systems

    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
    Cartney
    -0.69
     Dalai
    -0.66
     Concordia
    -0.61
    Datuak
    -0.59
     Harding
    -0.59
    airro
    -0.57
     Krone
    -0.56
    corrhi
    -0.55
     Gonzales
    -0.54
     Barrow
    -0.54
    POSITIVE LOGITS
    EOUT
    0.75
    WebControls
    0.75
    TimeUnit
    0.74
     aDecoder
    0.73
     veze
    0.71
     AssemblyCompany
    0.71
     متعلقه
    0.70
     outage
    0.69
     Vea
    0.69
     bacio
    0.68
    Activations Density 0.002%

    No Known Activations