© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38700
    Prev
    Next
    INDEX
    Explanations

    originally, recently

    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
     belonged
    -0.72
     wore
    -0.71
    came
    -0.69
    twas
    -0.68
     existed
    -0.65
     gehabt
    -0.65
     hadn
    -0.63
    didn
    -0.63
    曾
    -0.63
     came
    -0.62
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
     Fact
    0.55
     in
    0.50
     onCreateView
    0.49
     Shade
    0.47
     cytoplasmic
    0.47
     redistribute
    0.47
     getItemCount
    0.46
    исленность
    0.46
    نگی
    0.46
    Activations Density 0.451%

    No Known Activations