© 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. 30887
    Prev
    Next
    INDEX
    Explanations

    elements related to software architecture and data handling

    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
     kasarigan
    -0.77
    Билгалдахарш
    -0.70
    twimg
    -0.69
     nahilalakip
    -0.68
     EconPapers
    -0.65
     createSlice
    -0.63
    ⓧ
    -0.63
     صوتيه
    -0.62
    sizeCache
    -0.61
    agisse
    -0.61
    POSITIVE LOGITS
     mezza
    0.46
    yen
    0.46
     viewDidLoad
    0.44
     penyebab
    0.44
    oirs
    0.43
     policiales
    0.42
    unde
    0.42
     kū
    0.42
    最后一个
    0.42
     Yards
    0.42
    Activations Density 1.013%

    No Known Activations