© 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. 3-RES-MATRYOSHKA-DC
    7. 164
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathmatical notation

    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
    SharedCtor
    -0.87
    NameInMap
    -0.65
    basicConfig
    -0.54
     getItemCount
    -0.53
     nahilalakip
    -0.53
     autorytatywna
    -0.51
    simus
    -0.49
    Synonymes
    -0.49
    setVerticalGroup
    -0.48
    PreferredItem
    -0.48
    POSITIVE LOGITS
    dfrac
    0.87
    frac
    0.78
    towym
    0.70
    lainen
    0.63
     Langue
    0.63
     figliu
    0.63
    stackrel
    0.63
    cshtml
    0.63
     estekak
    0.63
     Savoy
    0.63
    Activations Density 0.452%

    No Known Activations