© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10559
    Prev
    Next
    INDEX
    Explanations

    patterns related to "IFT" labels, likely identifying data or signals associated with arrayed or encoded information

    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
    Negative Logits
    uinal
    -0.65
    Geme
    -0.61
    Бахар
    -0.60
     sánh
    -0.59
     Pend
    -0.58
     Meksiku
    -0.58
     Avo
    -0.57
     Lumber
    -0.57
    Parab
    -0.57
     Thessal
    -0.57
    POSITIVE LOGITS
     PK
    0.80
    textAppearance
    0.79
    viewtopic
    0.70
    :✨
    0.65
    XmlAccessorType
    0.63
    IFT
    0.63
    ::*;
    0.62
    anthin
    0.62
     MainAxisSize
    0.61
    erman
    0.60
    Activations Density 0.065%

    No Known Activations