© 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. 24933
    Prev
    Next
    INDEX
    Explanations

    references to hunting and related terms

    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
    httphttps
    -0.93
     Lessing
    -0.82
    arabe
    -0.78
     ProgressDialog
    -0.77
    tvguidetime
    -0.75
     MainAxisSize
    -0.75
    )}}{
    -0.71
    */}
    -0.70
     Sarm
    -0.70
    Amos
    -0.70
    POSITIVE LOGITS
     hunt
    1.78
     Hunt
    1.76
     Hunting
    1.70
    Hunt
    1.68
     HUNT
    1.68
     hunting
    1.66
     hunters
    1.65
    Hunting
    1.58
     Hunters
    1.57
     hunter
    1.54
    Activations Density 0.009%

    No Known Activations