© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5165
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opposition or contradiction

    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
    큼
    -0.60
     ostavi
    -0.57
     rivalry
    -0.54
    licon
    -0.53
     struggle
    -0.52
     يتيمه
    -0.52
     fair
    -0.51
    FetchType
    -0.50
    CAPTION
    -0.50
     Để
    -0.50
    POSITIVE LOGITS
     contrary
    3.28
     Contrary
    2.55
    Contrary
    2.31
    contr
    2.08
     unlike
    2.02
    unlike
    1.84
     contraire
    1.70
     contrário
    1.55
     contrario
    1.53
     Gegenteil
    1.46
    Activations Density 0.014%

    No Known Activations