© 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. 15548
    Prev
    Next
    INDEX
    Explanations

    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
     grim
    -0.85
    grim
    -0.84
     bleak
    -0.77
    Grim
    -0.72
    expandindo
    -0.69
     gloomy
    -0.69
     gloom
    -0.66
    tvguidetime
    -0.64
     TextAppearance
    -0.64
     Grim
    -0.63
    POSITIVE LOGITS
    mer
    0.71
    ly
    0.68
    ier
    0.60
    est
    0.57
    sp
    0.56
    room
    0.55
    spring
    0.53
    spot
    0.53
    ness
    0.52
    side
    0.52
    Activations Density 0.006%

    No Known Activations