© 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. 96782
    Prev
    Next
    INDEX
    Explanations

    cooking and 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
     contraire
    -0.46
     stability
    -0.43
     Audiodateien
    -0.42
    ysty
    -0.41
     Jednak
    -0.41
     Rady
    -0.40
    gtest
    -0.39
     inspiration
    -0.38
    ★★★★☆
    -0.38
     Pavlov
    -0.38
    POSITIVE LOGITS
     resourceCulture
    0.98
    ContentAsync
    0.80
     betweenstory
    0.79
     виправивши
    0.79
    enumii
    0.79
    parsedMessage
    0.79
    afficheront
    0.77
    Personendaten
    0.75
    NameInMap
    0.75
    enumi
    0.73
    Activations Density 0.002%

    No Known Activations