© 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. 24877
    Prev
    Next
    INDEX
    Explanations

    the visibility of class members in programming 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
     CreateTagHelper
    -1.12
     nahilalakip
    -0.94
    帖最后由
    -0.75
     ModelExpression
    -0.74
     noDo
    -0.70
     littéraire
    -0.69
    homonymie
    -0.68
    Hentet
    -0.68
     >=",
    -0.67
     hâte
    -0.67
    POSITIVE LOGITS
    quitous
    0.59
     Gar
    0.58
     mond
    0.56
    ếng
    0.56
     card
    0.54
     Card
    0.54
    udad
    0.53
    ارتمان
    0.52
     phone
    0.52
     الخ
    0.52
    Activations Density 0.001%

    No Known Activations