© 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. 28852
    Prev
    Next
    INDEX
    Explanations

    words and commands related to programming and data manipulation

    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
     "..\..\..\
    -0.81
     "..\..\
    -0.77
    brainly
    -0.72
    SequentialGroup
    -0.70
    ngdoc
    -0.66
    AsUp
    -0.66
    UnusedPrivate
    -0.65
     سكانية
    -0.65
     NKC
    -0.64
    tagHelperRunner
    -0.63
    POSITIVE LOGITS
     of
    0.51
    ارج
    0.49
     RoutedEventArgs
    0.49
     than
    0.48
     apologised
    0.47
     apologizing
    0.47
     perd
    0.47
    PROCESS
    0.47
     Cartes
    0.47
     Berge
    0.46
    Activations Density 0.066%

    No Known Activations