© 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. 21211
    Prev
    Next
    INDEX
    Explanations

    references to evidence or exhibits in a legal context

    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
    </b>
    -0.88
     seq
    -0.81
    ى
    -0.79
    er
    -0.78
    </i>
    -0.73
    seq
    -0.71
     Cronin
    -0.70
    רא
    -0.67
     Blount
    -0.67
    loadModel
    -0.67
    POSITIVE LOGITS
     Exhibit
    1.34
     Exhibits
    1.30
     EXHIBIT
    1.23
     exhibits
    1.22
     exhibit
    1.20
    Exhibit
    1.16
    EXHIBIT
    1.13
     Exhibition
    1.09
     EXHIB
    1.09
     exhibition
    1.05
    Activations Density 0.009%

    No Known Activations