© 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. 30838
    Prev
    Next
    INDEX
    Explanations

    legal terminology and questions related to court cases

    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
     issue
    -0.86
     issues
    -0.73
     matter
    -0.69
     matters
    -0.69
     topic
    -0.67
     sujet
    -0.66
    issue
    -0.65
     subject
    -0.65
    voer
    -0.63
     Topic
    -0.60
    POSITIVE LOGITS
    RegistryLite
    0.80
    RegressionTest
    0.80
    DockStyle
    0.65
     NSCoder
    0.62
    argout
    0.61
     وتسجيلات
    0.59
     CGRectMake
    0.58
     PHPUnit
    0.58
    inheritDoc
    0.57
    seteq
    0.57
    Activations Density 0.033%

    No Known Activations