© 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. 22-RES-MATRYOSHKA-DC
    7. 3114
    Prev
    Next
    INDEX
    Explanations

    square brackets inside of technical diagrams in abstract math

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    GRANTED
    -0.45
     egret
    -0.44
     PMS
    -0.44
     devol
    -0.44
     stihl
    -0.44
     mangá
    -0.42
    Anlage
    -0.42
     GoogleFonts
    -0.41
     Immanuel
    -0.41
     Wallflower
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.75
    
    0.70
     препратки
    0.68
     actionTypes
    0.64
    uxxxx
    0.62
    rrggbb
    0.62
     ExecuteAsync
    0.61
     بيها
    0.60
     Holl
    0.60
     snippetHide
    0.59
    Activations Density 0.002%

    No Known Activations