© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    references to a specific code element, namely the closing bracket or square bracket symbol

    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
    rungsseite
    -0.94
    enumi
    -0.86
    sidemargin
    -0.86
     <=",
    -0.86
    PerformLayout
    -0.84
    featureID
    -0.84
    ChildScrollView
    -0.83
    ]--;
    -0.82
    GraphicsUnit
    -0.79
    __":
    -0.78
    POSITIVE LOGITS
    ](
    3.22
    )](
    2.00
    "](
    1.52
     https
    1.04
    ![](
    1.03
    https
    1.00
    ```
    0.87
    >(
    0.84
     [](
    0.82
    ]()
    0.82
    Activations Density 0.011%

    No Known Activations