© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15910
    Prev
    Next
    INDEX
    Explanations

    the presence of code snippets related to defining and parsing functions or methods

    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
    crow
    -0.55
     pre
    -0.54
    æus
    -0.52
    sette
    -0.51
    dymyr
    -0.51
    сшта
    -0.50
    wählen
    -0.49
     ung
    -0.49
     upp
    -0.48
    handa
    -0.47
    POSITIVE LOGITS
     propOrder
    0.96
     autorytatywna
    0.84
    complexType
    0.84
    brainly
    0.80
    JspWriter
    0.79
    PhysRev
    0.76
    enumi
    0.75
     nakalista
    0.75
     suprême
    0.73
    Hentet
    0.72
    Activations Density 0.025%

    No Known Activations