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. 0-CLT-HP
    4. 826
    Prev
    Next
    INDEX
    Explanations

    welcome messages

    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
     welcome
    -1.66
     Welcome
    -1.35
    welcome
    -1.35
     welcomed
    -1.27
     WELCOME
    -1.26
    Welcome
    -1.16
    WELCOME
    -1.09
     welcomes
    -1.06
     welkom
    -1.02
     welcoming
    -0.99
    POSITIVE LOGITS
    e
    0.91
    eing
    0.62
    er
    0.59
    eh
    0.57
    erii
    0.57
    erent
    0.55
    betic
    0.54
    eme
    0.54
    erle
    0.53
    inkle
    0.53
    Activations Density 1.029%

    No Known Activations