© 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. 5692
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or pleasure

    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
    цы
    -0.53
    lisi
    -0.50
    rimer
    -0.49
    NegativeButton
    -0.49
     kül
    -0.49
    GroupName
    -0.49
     saith
    -0.49
    fect
    -0.48
     aident
    -0.46
    流れ
    -0.46
    POSITIVE LOGITS
     enjoy
    2.91
     Enjoy
    2.83
    enjoy
    2.77
     enjoyed
    2.69
     ENJOY
    2.66
    Enjoy
    2.56
     enjoying
    2.52
     enjoys
    2.44
     enjoyment
    2.22
    ENJOY
    2.17
    Activations Density 0.005%

    No Known Activations