© 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. 3-RES-MATRYOSHKA-DC
    7. 2134
    Prev
    Next
    INDEX
    Explanations

    lines of code defining static variables

    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
    abstractmethod
    -0.83
    رشف
    -0.82
     myſelf
    -0.75
    override
    -0.74
     themſelves
    -0.74
     pleaſure
    -0.73
     ویکی‌پدیای
    -0.72
     theſe
    -0.71
     Jefus
    -0.70
     itſelf
    -0.68
    POSITIVE LOGITS
     static
    1.59
     Static
    0.98
    Static
    0.84
     STATIC
    0.71
    静态
    0.71
    InitVars
    0.61
     conta
    0.52
    acre
    0.50
     Fortune
    0.50
    MLLoader
    0.50
    Activations Density 0.010%

    No Known Activations