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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1022
    Prev
    Next
    INDEX
    Explanations

    Sun

    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
     sun
    -0.97
     Sun
    -0.89
    Sun
    -0.74
     
    -0.60
     so
    -0.59
     most
    -0.57
     former
    -0.56
    <eos>
    -0.55
     new
    -0.52
     program
    -0.52
    POSITIVE LOGITS
     Efq
    1.05
    :✨
    0.96
     propOrder
    0.94
    нгред
    0.93
     ―――――
    0.93
     تانيه
    0.92
     ――――――――
    0.90
     pleaſure
    0.90
     ſind
    0.89
     feroit
    0.89
    Activations Density 0.018%

    No Known Activations