© 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. 350
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, formulas, and symbols

    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
     nahilalakip
    -1.01
     mapStateToProps
    -0.95
    mapStateToProps
    -0.85
    AccessFile
    -0.85
     ControllerBase
    -0.82
     Patro
    -0.81
     useRouter
    -0.79
     >=",
    -0.79
    ANDUM
    -0.77
    antMatchers
    -0.76
    POSITIVE LOGITS
     E
    1.22
    E
    1.03
     Eb
    0.99
     EG
    0.98
     e
    0.98
     Egger
    0.92
     Eg
    0.91
     Esk
    0.90
     EB
    0.89
     Estrada
    0.86
    Activations Density 5.073%

    No Known Activations