© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 508
    Prev
    Next
    INDEX
    Explanations

    LaTeX math subscripts and superscripts

    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
     отношению
    -0.51
     especially
    -0.45
    الثة
    -0.44
    FileDescriptor
    -0.43
     крайней
    -0.42
     procedimento
    -0.41
     دوم
    -0.40
     Especially
    -0.40
     dentaire
    -0.40
    Jäh
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    1.12
    bootstrapcdn
    0.94
    ConstraintMaker
    0.94
     يتيمه
    0.92
     كومونز
    0.88
     autorytatywna
    0.85
     nahilalakip
    0.84
    WaitGroup
    0.83
     gynhyrchwyd
    0.81
     فريبيس
    0.81
    Activations Density 1.274%

    No Known Activations