© 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. 17298
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming language syntax, especially in URLs and variable naming conventions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     expression
    -0.59
     Courant
    -0.52
     getir
    -0.50
    ORB
    -0.48
    Landing
    -0.48
     hinzu
    -0.47
     Expression
    -0.47
     lap
    -0.47
     meneg
    -0.47
    lap
    -0.46
    POSITIVE LOGITS
    startswith
    0.96
     AssemblyTitle
    0.86
     AssemblyVersion
    0.85
     betweenstory
    0.84
    LookAnd
    0.83
     kaarangay
    0.82
    bewerken
    0.72
    webElementXpaths
    0.72
    RegressionTest
    0.70
    AddHtmlAttribute
    0.68
    Activations Density 0.029%

    No Known Activations