© 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. 119
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific LaTeX-like math notation involving dollar signs and aligned environments

    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
     defaultstate
    -0.56
     requ
    -0.52
    ItemBackground
    -0.50
     tret
    -0.48
    softc
    -0.47
    مقاله
    -0.47
    ʹ
    -0.47
     extruder
    -0.47
    /";
    -0.46
     вере
    -0.46
    POSITIVE LOGITS
     $
    3.05
     $\
    1.98
     ($
    1.91
     $\$
    1.87
     $(
    1.85
    |}{$
    1.84
    $
    1.81
    ($
    1.77
    {$
    1.73
    ~$
    1.71
    Activations Density 1.748%

    No Known Activations