© 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. 2-RES-MATRYOSHKA-DC
    7. 3176
    Prev
    Next
    INDEX
    Explanations

    patterns involving mathematical symbols, equations, or LaTeX notation

    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
    </em>
    -0.61
    </code>
    -0.52
     $
    -0.52
    ”
    -0.50
     however
    -0.46
    “
    -0.46
    </i>
    -0.45
     inflater
    -0.45
    <strong>
    -0.45
     Aplica
    -0.44
    POSITIVE LOGITS
     للاسماء
    1.05
    LookAnd
    1.01
    ReusableCell
    0.91
    цездатний
    0.88
    AnchorStyles
    0.84
    yntaxException
    0.82
    XMLSchema
    0.81
    شهاد
    0.79
     Efq
    0.79
    ftagPool
    0.78
    Activations Density 1.323%

    No Known Activations