© 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. 45175
    Prev
    Next
    INDEX
    Explanations

    single or recent

    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
     démission
    -0.52
     atteinte
    -0.50
     présenter
    -0.47
     organisée
    -0.47
     مشين
    -0.47
     présentés
    -0.47
     Socialista
    -0.47
     ostavi
    -0.46
     considère
    -0.46
    onatos
    -0.46
    POSITIVE LOGITS
     Paglinawan
    0.66
    Према
    0.62
     weeks
    0.59
    جمعیت
    0.58
    raza
    0.58
     δὲ
    0.57
    protoimpl
    0.57
     oprot
    0.56
    SizeF
    0.55
     years
    0.55
    Activations Density 0.533%

    No Known Activations