© 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. 710
    Prev
    Next
    INDEX
    Explanations

    parts of words, acronyms, or unusual word compositions that contain "i" or "ili"

    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
     שוליים
    -0.87
     للمعارف
    -0.85
    談社
    -0.71
    ndra
    -0.65
    Magdalena
    -0.65
    cinogenicity
    -0.64
    րջ
    -0.64
     חיצוניים
    -0.63
    hra
    -0.62
    oczes
    -0.61
    POSITIVE LOGITS
    ili
    1.05
     SIS
    1.03
     GIP
    1.00
     Pits
    0.93
     Richie
    0.92
     Militia
    0.92
    Ili
    0.92
    iii
    0.92
     CSI
    0.92
    Mip
    0.91
    Activations Density 5.484%

    No Known Activations