© 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. 1-CLT-HP
    7. 12281
    Prev
    Next
    INDEX
    Explanations

    a

    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
     становника
    -0.82
    Autoritní
    -0.81
     الرياضيه
    -0.79
    fjspx
    -0.77
     Meksiku
    -0.75
     Мексичка
    -0.75
     disambiguazione
    -0.74
     Paglinawan
    -0.73
     cherchés
    -0.72
    ientôt
    -0.72
    POSITIVE LOGITS
     set
    0.54
     few
    0.50
     lot
    0.47
     wide
    0.47
     limited
    0.45
    set
    0.43
    alignSelf
    0.43
    ques
    0.42
     firm
    0.42
    wide
    0.40
    Activations Density 0.041%

    No Known Activations