© 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. 23298
    Prev
    Next
    INDEX
    Explanations

    terms related to halls of fame and induction into them

    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
     assignment
    -0.64
    assignment
    -0.60
     award
    -0.58
    ASSIGN
    -0.58
    nitten
    -0.57
     Assignment
    -0.56
    Fotografía
    -0.55
    Assignment
    -0.54
    idend
    -0.54
     assign
    -0.52
    POSITIVE LOGITS
    BeginContext
    0.77
    RRect
    0.74
    
    0.74
     autorytatywna
    0.70
    ThroughAttribute
    0.63
    UpInside
    0.63
     חיצוניים
    0.62
     HOF
    0.62
    webElementXpaths
    0.61
    GOTREF
    0.61
    Activations Density 0.005%

    No Known Activations