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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14896
    Prev
    Next
    INDEX
    Explanations

    patterns related to code snippets, specifically blocks involving importing, class definitions, and data structures

    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
    WebVitals
    -1.14
     виправивши
    -0.84
    mapping
    -0.70
     onAnimation
    -0.68
    CppMethod
    -0.68
    //
    -0.66
    enheim
    -0.66
    TypedDataSet
    -0.65
    GraphicsUnit
    -0.65
    AddHtmlAttribute
    -0.63
    POSITIVE LOGITS
     câte
    0.66
    rdom
    0.58
     rând
    0.54
    hashMap
    0.53
     hindurch
    0.52
     utilisez
    0.52
     Inscrivez
    0.52
     căr
    0.51
     combien
    0.51
     filter
    0.50
    Activations Density 0.038%

    No Known Activations