© 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. 0-RES-MATRYOSHKA-DC
    7. 11958
    Prev
    Next
    INDEX
    Explanations

    references to technical identifiers related to code or configuration, specifically instances of the suffix "iler" and the word "ppy" indicating different variations of this pattern

    oai_token-act-pair · gpt-4.1-nano
    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
    
    -0.60
    helia
    -0.56
    }{|
    -0.54
     offline
    -0.52
     ويكيميديا
    -0.52
    Offline
    -0.51
     ô
    -0.50
    +#+#
    -0.50
     Offline
    -0.49
     fact
    -0.48
    POSITIVE LOGITS
    iler
    1.50
    ILER
    1.30
    ilers
    1.29
    culature
    0.95
    iring
    0.82
    ppy
    0.82
    ilin
    0.73
    iline
    0.73
     NSCoder
    0.72
    ileri
    0.71
    Activations Density 0.002%

    No Known Activations