© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    patterns of structural or formatting markers in text, such as data templates, code snippets, or markup tags

    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
    
    -1.01
    談社
    -0.81
     متعلقه
    -0.80
     nakalista
    -0.73
    RenderAtEndOf
    -0.71
     كومونز
    -0.69
    揄
    -0.69
    styleType
    -0.68
    suya
    -0.68
    APORE
    -0.67
    POSITIVE LOGITS
                
    1.50
                                
    0.94
                 
    0.86
    0.74
                                   
    0.71
    0.71
    0.69
    teen
    0.65
               
    0.64
     tetto
    0.61
    Activations Density 0.131%

    No Known Activations