© 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. 18-RES-MATRYOSHKA-DC
    7. 617
    Prev
    Next
    INDEX
    Explanations

    blocks of code from Javascript unit tests, specifically the `describe`, `it`, and `expect` keywords

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.68
    unmodifiable
    -0.62
     BoxDecoration
    -0.61
    AnchorStyles
    -0.59
    #+#
    -0.57
     Vikipedi
    -0.57
    GraphicsUnit
    -0.56
     GoogleFonts
    -0.56
    LEncoder
    -0.55
    HtmlAttribute
    -0.54
    POSITIVE LOGITS
     test
    1.72
     tests
    1.61
     Test
    1.58
     testing
    1.54
     Tests
    1.43
    Test
    1.42
     Testing
    1.41
     TEST
    1.41
     tested
    1.29
    test
    1.28
    Activations Density 0.849%

    No Known Activations