© 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. 32363
    Prev
    Next
    INDEX
    Explanations

    lines of code containing error handling or logging statements

    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
     Gera
    -0.50
     near
    -0.50
    REM
    -0.49
     ‘
    -0.47
    стру
    -0.47
     haue
    -0.47
     Hau
    -0.47
     MV
    -0.47
     Lampe
    -0.47
    але
    -0.47
    POSITIVE LOGITS
    findpost
    1.05
    SharedDtor
    1.02
    AndEndTag
    0.99
    WriteTagHelper
    0.97
    StoryboardSegue
    0.97
    contentLoaded
    0.94
    таратура
    0.91
    évaluateur
    0.90
    ContentAsync
    0.88
    تقاوى
    0.87
    Activations Density 0.002%

    No Known Activations