© 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-CLT-HP
    7. 92858
    Prev
    Next
    INDEX
    Explanations

    encouragement/motivation

    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
     encourage
    -1.20
     encourages
    -0.97
     Encourage
    -0.94
     encouraged
    -0.93
     motivate
    -0.87
    Encourage
    -0.82
     encouraging
    -0.82
     encouragement
    -0.81
     discourage
    -0.77
     discou
    -0.69
    POSITIVE LOGITS
     Efq
    1.04
     myſelf
    0.84
     $_"
    0.81
     themſelves
    0.79
     Monfieur
    0.79
     Theſe
    0.78
    ^(@)
    0.75
    ">//
    0.75
    Tembelea
    0.75
    ſelf
    0.74
    Activations Density 0.095%

    No Known Activations