© 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. 18580
    Prev
    Next
    INDEX
    Explanations

    words related to legal compliance and applicability of laws

    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
    ageo
    -0.83
     Rukh
    -0.76
    extAlignment
    -0.69
     مرئيه
    -0.67
     bpy
    -0.64
    MENAFN
    -0.63
    apimachinery
    -0.60
     Brow
    -0.60
     coreano
    -0.60
    barrow
    -0.60
    POSITIVE LOGITS
    applicable
    0.90
     applicable
    0.79
     Applicable
    0.79
    Applicable
    0.67
    Geographie
    0.63
     APPLICABLE
    0.63
    áns
    0.62
    первых
    0.57
     externes
    0.57
    DEPEND
    0.57
    Activations Density 0.004%

    No Known Activations