© 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. 23662
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement roles or titles

    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
    ‗
    -0.70
    jstor
    -0.68
    carpus
    -0.63
     fou
    -0.60
    Collegamenti
    -0.59
     continents
    -0.58
    ntos
    -0.56
    abancı
    -0.56
    liani
    -0.55
    pete
    -0.54
    POSITIVE LOGITS
     Sheriff
    1.44
     sheriff
    1.44
    Sheriff
    1.34
     sher
    1.22
     SHER
    1.21
     Deputies
    1.20
     deputies
    1.18
    uties
    1.14
     Sher
    1.05
     Sherwood
    0.92
    Activations Density 0.008%

    No Known Activations