© 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. 0-RES-MATRYOSHKA-DC
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    neural signals associated with fatigue or tiredness

    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
     exhausted
    -0.79
     exhaust
    -0.75
     depleted
    -0.71
     exhausting
    -0.60
     bored
    -0.58
     Exhaust
    -0.58
     depletion
    -0.58
    exhaust
    -0.58
     Exhaus
    -0.57
    IonicModule
    -0.57
    POSITIVE LOGITS
     fatigue
    2.77
     Fatigue
    2.45
    fatigue
    2.34
    Fatigue
    2.09
     fatig
    1.45
     fatigued
    1.13
     fatiga
    1.13
     fatigu
    1.08
     tiredness
    0.91
     متعلقه
    0.89
    Activations Density 0.001%

    No Known Activations