© 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. 9
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-like structures, possibly C or C++ based on the presence of '++' and conditional logic structures

    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
    født
    -0.47
    Â
    -0.45
     EXTR
    -0.45
     FetchType
    -0.44
    -0.43
    ItemGroup
    -0.43
    tsy
    -0.43
    kani
    -0.42
     vagas
    -0.42
     estimés
    -0.42
    POSITIVE LOGITS
            
    1.55
                
    1.48
              
    1.35
             
    1.31
                    
    1.26
          
    1.23
           
    1.20
                 
    1.19
               
    1.17
                  
    1.11
    Activations Density 3.099%

    No Known Activations