© 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. 14888
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cop" in various forms and contexts

    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
     Montana
    -0.74
    htä
    -0.71
    tvguidetime
    -0.71
    Xaml
    -0.68
     Conway
    -0.66
    Kalb
    -0.66
     Schle
    -0.66
    __((
    -0.65
     Guill
    -0.64
     Tie
    -0.63
    POSITIVE LOGITS
     Copeland
    1.16
     Cop
    1.01
     COP
    0.98
    Cop
    0.98
     Cope
    0.96
    cop
    0.94
     cop
    0.93
     Coping
    0.90
    Cope
    0.88
     coping
    0.87
    Activations Density 0.006%

    No Known Activations