© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2569
    Prev
    Next
    INDEX
    Explanations

    various kinds of exceptions in computer code

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     error
    -0.89
     ERROR
    -0.85
    error
    -0.81
     Error
    -0.80
    Error
    -0.80
     Errors
    -0.79
     errors
    -0.77
     错误
    -0.75
     ErrorCode
    -0.72
     uſed
    -0.72
    POSITIVE LOGITS
     catch
    0.79
    catch
    0.69
     ex
    0.67
     Exception
    0.66
     caught
    0.62
     Catch
    0.61
    Exception
    0.61
     exception
    0.59
     Ex
    0.59
     архивлан
    0.57
    Activations Density 0.104%

    No Known Activations