© 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. 20990
    Prev
    Next
    INDEX
    Explanations

    the presence of structured code or programming syntax

    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
     belirt
    -0.48
    SizeMode
    -0.47
    以上就是
    -0.44
     interessanti
    -0.44
    Hes
    -0.42
     professionali
    -0.42
    }'.
    -0.42
     nazionali
    -0.42
    følgelig
    -0.41
     ennen
    -0.41
    POSITIVE LOGITS
    tvguidetime
    1.09
    rungsseite
    0.90
     '\\;'
    0.82
     ddelweddau
    0.79
    ьаж
    0.77
    IndentedString
    0.75
    webElementXpaths
    0.75
    verwijspagina
    0.74
     kasarigan
    0.73
    Välislingid
    0.73
    Activations Density 0.313%

    No Known Activations