© 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. 9379
    Prev
    Next
    INDEX
    Explanations

    fragments of code that indicate error handling or logic checks

    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
    bleau
    -0.90
     Kork
    -0.81
    '},
    -0.79
    -0.79
    มาณ
    -0.78
    -0.76
     propOrder
    -0.76
    expandindo
    -0.75
     Coward
    -0.70
    BrowserModule
    -0.69
    POSITIVE LOGITS
     Kershaw
    0.80
     Arteta
    0.75
     transcripts
    0.74
     Rivas
    0.72
     Scully
    0.71
     ECS
    0.71
    alanta
    0.70
     Moseley
    0.68
     člá
    0.67
     avan
    0.67
    Activations Density 0.120%

    No Known Activations