© 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. 6-RES-MATRYOSHKA-DC
    7. 593
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and syntax, particularly LaTeX

    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
    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
    mew
    -0.68
     Stoll
    -0.60
    miary
    -0.59
    zzar
    -0.59
     McIn
    -0.59
     McIntyre
    -0.58
    ivät
    -0.58
    źni
    -0.58
    knock
    -0.57
     Savage
    -0.54
    POSITIVE LOGITS
     فريبيس
    1.16
    abestanden
    0.91
    Personensuche
    0.78
    الإنجليزية
    0.77
     defaultstate
    0.76
     gynhyrchwyd
    0.76
    </strong>
    0.75
     ویکی‌پدی
    0.73
     يتيمه
    0.73
     pinulongan
    0.71
    Activations Density 2.201%

    No Known Activations