© 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. 1-CLT-HP
    7. 14417
    Prev
    Next
    INDEX
    Explanations

    depression and negative emotions

    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
    awtextra
    -0.95
    
    -0.93
    tagHelperRunner
    -0.83
     createState
    -0.82
     kaynağından
    -0.81
    存于互联网档案馆
    -0.79
    ConstraintMaker
    -0.79
     EconPapers
    -0.78
     للاسماء
    -0.73
     للمعارف
    -0.72
    POSITIVE LOGITS
     dynamics
    0.47
     pron
    0.47
     symptoms
    0.46
     Burrow
    0.44
     patients
    0.44
     letters
    0.43
    gans
    0.43
     consign
    0.43
     complaints
    0.42
     Scherer
    0.42
    Activations Density 0.009%

    No Known Activations