© 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. 32530
    Prev
    Next
    INDEX
    Explanations

    phrases related to compliance and disobedience in legal contexts

    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
    tanleria
    -0.62
     Acts
    -0.61
    machus
    -0.58
     acts
    -0.56
    cierto
    -0.55
    AndroidJUnit
    -0.54
     referenties
    -0.54
    arakhand
    -0.54
    ynku
    -0.54
     Savoie
    -0.53
    POSITIVE LOGITS
     insuffisamment
    0.60
    Portály
    0.57
    ̉
    0.54
    enumii
    0.54
     BorderRadius
    0.53
    !*\
    0.52
     physical
    0.51
     cerevisiae
    0.51
    TryParse
    0.51
    脚注の使い方
    0.51
    Activations Density 0.068%

    No Known Activations