© 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. 0-RES-MATRYOSHKA-DC
    7. 11952
    Prev
    Next
    INDEX
    Explanations

    references to the concept of health and well-being

    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
     great
    -0.56
    фіка
    -0.47
    ároz
    -0.47
    uaikan
    -0.46
     ‘
    -0.46
     ground
    -0.45
    ыр
    -0.45
    ionario
    -0.44
     Hautes
    -0.44
     methyl
    -0.44
    POSITIVE LOGITS
    being
    1.71
     Wellbeing
    0.94
     poveznice
    0.93
     wellbeing
    0.92
    ChildScrollView
    0.88
    theless
    0.85
    хьтан
    0.84
    SourceChecksum
    0.82
    Being
    0.82
     Réponses
    0.82
    Activations Density 0.001%

    No Known Activations