© 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. 677
    Prev
    Next
    INDEX
    Explanations

    mathematical notation including the substring "ij"

    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
     itſelf
    -0.78
     ſtate
    -0.77
     juſt
    -0.74
     Darmstadt
    -0.70
     Duane
    -0.69
     reaſon
    -0.69
     houſe
    -0.69
     Borussia
    -0.67
     faſt
    -0.67
     resourceCulture
    -0.67
    POSITIVE LOGITS
    ij
    2.67
     ij
    1.63
    IJ
    1.49
     IJ
    1.18
     Zij
    1.15
    ijo
    1.08
     Mij
    1.02
    ijt
    1.01
     Nij
    1.00
    rij
    0.98
    Activations Density 0.144%

    No Known Activations