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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12896
    Prev
    Next
    INDEX
    Explanations

    whistle

    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
     whistles
    -0.99
     whistle
    -0.90
     Whistle
    -0.64
     виправивши
    -0.63
     StatefulWidget
    -0.62
     whistled
    -0.62
     مرئيه
    -0.62
     GenerationType
    -0.61
    ComponentScan
    -0.61
     "..\..\
    -0.60
    POSITIVE LOGITS
    addPreferredGap
    0.52
    endphp
    0.48
    .$.
    0.45
    requestCode
    0.45
     ?>>
    0.44
    CSA
    0.44
    setViewportView
    0.44
     for
    0.43
    hintText
    0.43
    jois
    0.43
    Activations Density 0.042%

    No Known Activations