© 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. 15667
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and procedural concepts, especially those indicating effect or authority

    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
    ($__
    -0.68
     bezeichneter
    -0.68
     ✭✭
    -0.68
    ніципалі
    -0.66
    stackrel
    -0.63
    цезда
    -0.63
    TestingModule
    -0.63
    GraphicsUnit
    -0.62
    gonic
    -0.60
     alimentare
    -0.60
    POSITIVE LOGITS
     effectively
    0.73
    Effective
    0.62
     effective
    0.60
    Implicit
    0.58
     Effectively
    0.57
    effectively
    0.57
     implied
    0.55
    effective
    0.54
     Effective
    0.54
     equivalent
    0.53
    Activations Density 0.074%

    No Known Activations