© 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. 10488
    Prev
    Next
    INDEX
    Explanations

    positive feelings

    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
     pleasant
    -1.09
     enjoyable
    -0.93
    pleasant
    -0.85
     agreeable
    -0.84
     pleasantly
    -0.79
     delightful
    -0.75
    BufferException
    -0.73
    WriteTagHelper
    -0.73
    GMENT
    -0.69
     CURIAM
    -0.67
    POSITIVE LOGITS
    تقاوى
    0.57
    kloped
    0.48
     quotidien
    0.42
    edoc
    0.41
    sme
    0.41
     Tycoon
    0.41
    cooled
    0.41
    PERT
    0.41
     consumo
    0.39
    aarrggbb
    0.38
    Activations Density 0.011%

    No Known Activations