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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 459
    Prev
    Next
    INDEX
    Explanations

    structured data or elements related to serialization and definitions within code, particularly involving JSON or programming constructs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    formKey
    -0.97
    /**
    -0.94
    CopyWith
    -0.91
     setuptools
    -0.89
     HasFactory
    -0.87
     CreateTagHelper
    -0.86
    BuildContext
    -0.84
    GEBURTSDATUM
    -0.84
    IsContent
    -0.84
    InjectAttribute
    -0.82
    POSITIVE LOGITS
      
    1.47
       
    1.20
    0.94
         
    0.87
        
    0.84
          
    0.82
    ：　
    0.77
           
    0.75
    　
    0.70
    
    0.67
    Activations Density 1.269%

    No Known Activations