© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    instances of dissent in legal or judicial 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
    Not in Any Lists

    No Comments

    Negative Logits
    CodeAttribute
    -0.61
     Legendre
    -0.61
    vician
    -0.60
     Lucas
    -0.57
     laces
    -0.57
    hmigung
    -0.57
     MainAxisSize
    -0.57
    uurs
    -0.57
     thiệu
    -0.56
     statusCode
    -0.56
    POSITIVE LOGITS
     dissent
    0.98
     Dissent
    0.97
     dissenting
    0.75
     Diss
    0.72
     DISS
    0.70
     Vass
    0.65
     diss
    0.65
    Diss
    0.62
    ostream
    0.59
    issent
    0.58
    Activations Density 0.004%

    No Known Activations