Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16561
    Prev
    Next
    INDEX
    Explanations

    code snippets that describe trees via nested indentation and the words "child", "grandchild", and "parent".

    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
    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
    protoimpl
    -0.77
     وتسجيلات
    -0.73
    makeConstraints
    -0.69
     fraî
    -0.67
    expandindo
    -0.65
     transfieras
    -0.63
     CreateTagHelper
    -0.62
    Diweddarwch
    -0.62
     Италијани
    -0.60
    IndentedString
    -0.60
    POSITIVE LOGITS
     الحره
    0.71
    numerusform
    0.51
    们
    0.50
    atism
    0.48
     sponsor
    0.47
    SuppressLint
    0.46
    didSet
    0.46
    Transkript
    0.46
    們
    0.45
    去吧
    0.44
    Activations Density 0.044%

    No Known Activations