© 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. 14378
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal actions and decisions

    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
     autorytatywna
    -0.82
    expandindo
    -0.80
     camicia
    -0.78
     namorados
    -0.77
    seamnă
    -0.77
     Schild
    -0.76
     acela
    -0.75
     regno
    -0.73
     phoneNumber
    -0.72
     storici
    -0.72
    POSITIVE LOGITS
     disposition
    1.37
     disposed
    1.33
     dispose
    1.32
    disposition
    1.22
     dispositions
    1.20
     Disposition
    1.16
    Disposition
    1.08
     disposing
    1.05
     disposal
    1.04
    disposed
    1.04
    Activations Density 0.007%

    No Known Activations