© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    instances of the word "busy" and its variations

    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
     Balth
    -0.66
    Schneider
    -0.66
     Farah
    -0.65
     altars
    -0.64
     Cowell
    -0.62
     Schweitzer
    -0.62
     camels
    -0.61
     Cabello
    -0.61
     starboard
    -0.60
     Matth
    -0.60
    POSITIVE LOGITS
     Busy
    1.73
     busy
    1.60
    Busy
    1.55
    busy
    1.54
     busiest
    1.09
    BUSY
    1.07
     sibuk
    0.90
     ocupado
    0.85
    忙
    0.80
     hectic
    0.79
    Activations Density 0.004%

    No Known Activations