© 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. 2-RES-MATRYOSHKA-DC
    7. 7550
    Prev
    Next
    INDEX
    Explanations

    references to undercover law enforcement agents involved in drug conspiracy cases

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Theſe
    -0.96
     ―――――
    -0.93
     myſelf
    -0.92
    StoryboardSegue
    -0.91
     Workmen
    -0.86
     Anſ
    -0.86
     doubtnut
    -0.86
     ་་
    -0.86
     itſelf
    -0.85
     Houſe
    -0.84
    POSITIVE LOGITS
     He
    0.57
     (
    0.55
     he
    0.55
     I
    0.54
     his
    0.52
     sie
    0.52
     Ra
    0.52
     our
    0.52
    ropol
    0.52
     Crime
    0.52
    Activations Density 2.568%

    No Known Activations