© 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. 18118
    Prev
    Next
    INDEX
    Explanations

    references to judges and magistrates in a legal context

    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
    تقاوى
    -0.56
     Ver
    -0.55
    <eos>
    -0.55
    UpInside
    -0.50
    orkin
    -0.50
     E
    -0.50
    üste
    -0.50
    dau
    -0.49
    ing
    -0.49
     domin
    -0.48
    POSITIVE LOGITS
     Magistrate
    1.04
     propOrder
    1.04
     magistrate
    1.00
     magistrates
    0.93
     Magistrates
    0.91
     VIAF
    0.81
     Theſe
    0.79
     Magist
    0.79
    MessageOf
    0.78
     Winaray
    0.77
    Activations Density 0.005%

    No Known Activations