© 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. 1-RES-MATRYOSHKA-DC
    7. 61
    Prev
    Next
    INDEX
    Explanations

    patterns of highly repetitive or strongly emphasized symbols, often with nested or complex 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
     *
    -0.68
    <i>
    -0.59
    </i>
    -0.58
     •
    -0.56
    ′
    -0.56
     \\
    -0.56
    ⋅
    -0.56
     '
    -0.55
     *
    -0.55
     ‘
    -0.50
    POSITIVE LOGITS
    **
    3.05
     **
    2.48
    .**
    2.39
    )**
    2.38
    ]**
    2.34
    **)
    2.23
    **,
    2.16
    **.
    2.09
    (**
    2.08
    :**
    2.05
    Activations Density 2.817%

    No Known Activations