© 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. 6037
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to string delimiters and escape characters

    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
    ='
    -1.03
    ="
    -0.98
    =’
    -0.77
    =\"
    -0.65
    =['
    -0.62
    =”
    -0.61
    =('
    -0.60
    ={'
    -0.60
    =\
    -0.56
    =(
    -0.56
    POSITIVE LOGITS
    "]
    0.87
     Efq
    0.85
    "])
    0.84
    OGND
    0.82
     Roskov
    0.82
    .")
    0.80
     ་་
    0.80
    ')")
    0.80
    verläs
    0.77
    "){
    0.77
    Activations Density 0.216%

    No Known Activations