© 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. 31007
    Prev
    Next
    INDEX
    Explanations

    law-related terms and specific legal conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nawr
    -0.81
    ResumeLayout
    -0.79
    出版年
    -0.74
    IsContent
    -0.73
    Portail
    -0.70
     للاسماء
    -0.69
     conclure
    -0.69
    RenderAtEndOf
    -0.68
    WebVitals
    -0.68
    новниш
    -0.66
    POSITIVE LOGITS
    0
    0.90
    lably
    0.72
    ０
    0.66
    modb
    0.57
     வே
    0.55
     identity
    0.54
     Mith
    0.54
    bole
    0.54
     Doy
    0.54
    Loh
    0.53
    Activations Density 0.023%

    No Known Activations