© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94476
    Prev
    Next
    INDEX
    Explanations

    heat

    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
    ثیر
    -0.40
     cucchiai
    -0.40
    șe
    -0.39
    奕
    -0.39
    تفصیلات
    -0.38
     toprak
    -0.38
    ussis
    -0.38
    chluss
    -0.37
     viață
    -0.37
     savent
    -0.37
    POSITIVE LOGITS
     heat
    1.02
     Heat
    1.00
     warm
    1.00
    warm
    0.99
     temperature
    0.98
     warmer
    0.97
     Warm
    0.95
     heats
    0.95
    Warm
    0.94
    temperature
    0.93
    Activations Density 0.002%

    No Known Activations