© 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. 16906
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming, specifically concerning code execution 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
     Superhosts
    -0.48
    berapa
    -0.48
    ortunadamente
    -0.47
     supposedly
    -0.44
    +#+
    -0.44
    Jeografia
    -0.44
     onData
    -0.43
     bastante
    -0.41
     mucha
    -0.41
     väldigt
    -0.40
    POSITIVE LOGITS
     виправивши
    1.02
    ValueStyle
    0.95
    ddots
    0.77
    NgModule
    0.76
    ագրություններ
    0.74
    denly
    0.70
     AssemblyTitle
    0.70
    NameInMap
    0.70
    تقاوى
    0.69
    +#+#
    0.68
    Activations Density 0.082%

    No Known Activations