© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    temperature

    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
     Temperature
    -0.81
     Himo
    -0.71
    Temperature
    -0.69
     Balloons
    -0.69
     Myself
    -0.67
     Tattoo
    -0.62
     Scissors
    -0.62
     Mies
    -0.62
    Balloon
    -0.60
     Tbsp
    -0.58
    POSITIVE LOGITS
     estekak
    0.68
    contentLoaded
    0.68
     שוליים
    0.58
    Kjelder
    0.56
     Administrativna
    0.55
     lenker
    0.54
    Források
    0.53
     autorytatywna
    0.53
    PropertyChanging
    0.53
    évaluateur
    0.52
    Activations Density 0.465%

    No Known Activations