© 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. 2-RES-MATRYOSHKA-DC
    7. 4969
    Prev
    Next
    INDEX
    Explanations

    patterns of hidden or masked content represented by the repeated presence of the '▁' character

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                    
    -0.66
     Rag
    -0.62
                                   
    -0.61
                   
    -0.60
    Câu
    -0.56
                  
    -0.56
     Fitz
    -0.56
    </h4>
    -0.54
     Guen
    -0.54
    ちら
    -0.53
    POSITIVE LOGITS
                                
    1.16
                               
    1.13
                              
    1.12
                             
    1.09
    1.08
    __':
    0.97
    __":
    0.95
     Scherer
    0.94
     SEDS
    0.94
     doInBackground
    0.94
    Activations Density 0.125%

    No Known Activations