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. 22-CLT-HP
    4. 74231
    Prev
    Next
    INDEX
    Explanations

    Interactions

    np_max-act-logits · 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
    ainville
    -0.65
    تقاوى
    -0.64
    EndInit
    -0.61
    expandindo
    -0.59
    BarStyle
    -0.59
     mile
    -0.57
    deelte
    -0.57
    tadır
    -0.57
    CppMethod
    -0.56
     blok
    -0.56
    POSITIVE LOGITS
    SuccessListener
    0.63
    Kontrola
    0.49
    SuppressLint
    0.48
    makeConstraints
    0.47
    lasia
    0.47
    CompleteListener
    0.47
    carnated
    0.45
     conclusão
    0.45
     turns
    0.44
    +:+
    0.43
    Activations Density 0.024%

    No Known Activations