© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38670
    Prev
    Next
    INDEX
    Explanations

    wells, wellbeing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wells
    -1.50
     wells
    -1.46
     Wells
    -1.23
     WELLS
    -1.13
    WELL
    -1.12
    Wells
    -1.11
     WELL
    -1.02
     well
    -1.02
     Wellbeing
    -0.99
     wellbeing
    -0.98
    POSITIVE LOGITS
    CrossRef
    0.60
     relâche
    0.57
     kasarigan
    0.56
     ejus
    0.54
    AsUp
    0.54
     maș
    0.54
     gratuits
    0.51
     uș
    0.50
     nicio
    0.49
     honte
    0.49
    Activations Density 0.032%

    No Known Activations