© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13848
    Prev
    Next
    INDEX
    Explanations

    references to treatment discontinuation or cessation

    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
    TagMode
    -1.01
     يتيمه
    -0.73
     Chwiliwch
    -0.70
     للمعارف
    -0.69
     InputDecoration
    -0.66
    сылкі
    -0.65
    NUMX
    -0.65
    MessageOf
    -0.63
     Pasa
    -0.60
     MessageBoxIcon
    -0.59
    POSITIVE LOGITS
     discontinued
    2.88
     discontin
    2.58
     discontinue
    2.48
     withdrawal
    0.65
     withdrawn
    0.65
    廃止
    0.63
     abandonné
    0.62
     withdraw
    0.62
     withdrawing
    0.61
     Withdrawal
    0.58
    Activations Density 0.001%

    No Known Activations