Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12350
    Prev
    Next
    INDEX
    Explanations

    admiration and enjoyment

    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
     feast
    -1.00
     Feast
    -0.76
     admire
    -0.68
    Feast
    -0.66
     feasts
    -0.62
     Infórmanos
    -0.58
     feasting
    -0.56
     propOrder
    -0.56
    GraphicsUnit
    -0.55
    horabuena
    -0.55
    POSITIVE LOGITS
    days
    0.66
    AsUp
    0.64
    AddHtmlAttribute
    0.63
    s
    0.58
    ments
    0.56
    RegressionTest
    0.55
    енча
    0.53
     getF
    0.51
    #
    0.50
    atoes
    0.50
    Activations Density 0.067%

    No Known Activations