© 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. 24-RES-MATRYOSHKA-DC
    7. 27
    Prev
    Next
    INDEX
    Explanations

    lines in JavaScript code snippets, especially those with indentation or containing keywords like "expect".

    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.24.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.24.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
    GraphicsUnit
    -0.59
    .[/
    -0.57
     seventh
    -0.56
    );
    -0.56
    }
    -0.53
    7
    -0.53
    ();
    -0.50
    ()]);
    -0.50
    בע
    -0.50
     ")");
    -0.50
    POSITIVE LOGITS
            
    1.53
                
    1.38
                    
    1.20
             
    1.15
              
    1.09
          
    1.04
           
    1.02
                 
    1.02
               
    0.99
                  
    0.95
    Activations Density 1.649%

    No Known Activations