© 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. 15056
    Prev
    Next
    INDEX
    Explanations

    references to recognition and awards in film and performance 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
     retired
    -0.75
     Retired
    -0.65
     retires
    -0.65
     retiring
    -0.63
    Retired
    -0.60
    retired
    -0.60
     retirees
    -0.55
     retraite
    -0.55
     vicini
    -0.53
     mö
    -0.51
    POSITIVE LOGITS
     schoolboy
    0.84
     propOrder
    0.81
     youth
    0.78
     kids
    0.78
     cadets
    0.78
     kid
    0.77
     Kids
    0.77
     youngsters
    0.77
     cadet
    0.77
     Youth
    0.76
    Activations Density 0.392%

    No Known Activations