© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 324
    Prev
    Next
    INDEX
    Explanations

    negative integers and code snippets

    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
     "))
    -0.58
     ")[
    -0.56
    arier
    -0.55
    ']):
    -0.54
    '>{
    -0.54
    /')
    -0.54
    ึ้น
    -0.53
    ')):
    -0.52
    )}>
    -0.51
    ')[
    -0.50
    POSITIVE LOGITS
     Monfieur
    0.85
     pleaſure
    0.83
     kasarigan
    0.81
     myſelf
    0.79
    AddTagHelper
    0.77
     Jefus
    0.77
     Diſ
    0.77
     Majefty
    0.76
    تفصیلات
    0.76
    ArrowToggle
    0.75
    Activations Density 1.877%

    No Known Activations