© 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. 1-CLT-HP
    7. 590
    Prev
    Next
    INDEX
    Explanations

    roasting

    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
     roasted
    -1.05
     roast
    -1.02
     Roast
    -0.96
     roasting
    -0.94
    roasted
    -0.89
     Roasted
    -0.86
    Roasted
    -0.79
    Roast
    -0.73
    abat
    -0.47
     regioni
    -0.47
    POSITIVE LOGITS
    enumi
    0.71
     TAMBÉM
    0.65
    CloseOperation
    0.63
     EconPapers
    0.63
     Signalez
    0.60
    ViewImports
    0.60
     صوتيه
    0.60
    camin
    0.58
     Infórmanos
    0.57
     Paglinawan
    0.56
    Activations Density 0.045%

    No Known Activations