© 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. 0-CLT-HP
    7. 40725
    Prev
    Next
    INDEX
    Explanations

    temperature and freedom

    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
     freedom
    -1.27
    freedom
    -1.14
     warmth
    -1.07
     Freedom
    -1.05
    Freedom
    -0.95
     FREEDOM
    -0.90
     liberté
    -0.75
     libertad
    -0.72
     freezing
    -0.71
     choice
    -0.68
    POSITIVE LOGITS
    s
    1.05
    windowFixed
    0.75
     Roskov
    0.73
    Personendaten
    0.65
     propOrder
    0.64
    hips
    0.63
     saites
    0.63
    OrNil
    0.62
     AssemblyCulture
    0.57
    ември
    0.55
    Activations Density 0.112%

    No Known Activations