© 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. 11773
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and summaries related to programming or software components

    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
     وتسجيلات
    -0.80
     Мексичка
    -0.75
    SequentialGroup
    -0.74
     resourceCulture
    -0.73
     للاسماء
    -0.70
     CreateTagHelper
    -0.70
    __(/*!
    -0.69
    msgTypes
    -0.67
    modb
    -0.66
     defaultstate
    -0.65
    POSITIVE LOGITS
     sağlar
    0.50
     verir
    0.44
    amis
    0.44
     strto
    0.44
    ingo
    0.41
    ุ
    0.41
    Ծանոթ
    0.40
    ix
    0.40
    鐸
    0.40
    Friendly
    0.40
    Activations Density 0.127%

    No Known Activations