© 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. 20968
    Prev
    Next
    INDEX
    Explanations

    coding structures and syntax used in programming, particularly involving data manipulation and function definitions

    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
    rawDesc
    -0.52
    bukkit
    -0.47
    Rptr
    -0.44
    jface
    -0.44
     board
    -0.43
    라이
    -0.42
     pen
    -0.41
    buya
    -0.40
    lapia
    -0.40
     intStringLen
    -0.40
    POSITIVE LOGITS
     snippetHide
    0.77
     مشين
    0.72
     estimés
    0.71
     testSet
    0.67
    findpost
    0.66
    Tikang
    0.66
     otomatig
    0.66
     demografica
    0.64
     contextLoads
    0.61
    KeySpec
    0.59
    Activations Density 0.183%

    No Known Activations