© 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. 2-RES-MATRYOSHKA-DC
    7. 2605
    Prev
    Next
    INDEX
    Explanations

    the initialization method for a class or module

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    webElementXpaths
    -0.70
    Turns
    -0.57
     prote
    -0.56
    lgica
    -0.56
    arxiv
    -0.55
    HasIndex
    -0.54
    protein
    -0.53
    LElement
    -0.53
     оригіналу
    -0.52
    プリング
    -0.52
    POSITIVE LOGITS
    init
    3.16
     init
    2.67
    Init
    2.11
     Init
    2.06
    INIT
    1.92
     INIT
    1.71
     initialization
    1.59
     Initialization
    1.47
     初始化
    1.43
    初始化
    1.40
    Activations Density 0.022%

    No Known Activations