© 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. 2-RES-MATRYOSHKA-DC
    7. 6548
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dis" or its variations

    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
     discretion
    -0.65
     disc
    -0.60
     Disc
    -0.60
     disk
    -0.60
     goutte
    -0.58
    cretion
    -0.56
    Disc
    -0.55
     dismissal
    -0.55
     discs
    -0.55
    fvar
    -0.55
    POSITIVE LOGITS
     dis
    2.81
     Dis
    1.21
    Dis
    1.16
    dis
    1.10
     dés
    0.91
    InputBorder
    0.84
     dise
    0.76
     autorytatywna
    0.76
    новниш
    0.75
     Genu
    0.73
    Activations Density 0.012%

    No Known Activations