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. 12584
    Prev
    Next
    INDEX
    Explanations

    celebrate

    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
    TagMode
    -0.89
     وتسجيلات
    -0.87
     prêtres
    -0.83
    ContentAsync
    -0.83
     stället
    -0.82
    AddTagHelper
    -0.81
     transfieras
    -0.81
    fitrión
    -0.81
    ValueStyle
    -0.79
     culturelles
    -0.79
    POSITIVE LOGITS
     all
    0.54
     mis
    0.53
     other
    0.50
     working
    0.50
     being
    0.48
     National
    0.44
     at
    0.43
     fl
    0.43
     with
    0.42
     processing
    0.42
    Activations Density 0.008%

    No Known Activations