© 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. 32114
    Prev
    Next
    INDEX
    Explanations

    legal terms related to jury outcomes and verdicts

    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
     Jury
    -1.16
    Jury
    -1.10
     jury
    -1.07
     juries
    -1.04
    jury
    -1.00
     jurors
    -0.83
     >=",
    -0.75
     juror
    -0.70
     Kuru
    -0.68
    AndEndTag
    -0.68
    POSITIVE LOGITS
    stateProvider
    0.59
    ress
    0.55
    حياتها
    0.55
    MTS
    0.54
    حياته
    0.53
     apporté
    0.52
    ########.
    0.52
     Down
    0.50
     المنت
    0.50
    废
    0.50
    Activations Density 0.033%

    No Known Activations