© 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. 45710
    Prev
    Next
    INDEX
    Explanations

    transcripts

    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
    PerformLayout
    -0.55
    Халык
    -0.52
    Segoe
    -0.50
     jScrollPane
    -0.50
    DebuggerNonUser
    -0.47
    تقاوى
    -0.45
    jsdelivr
    -0.45
    ADELPHIA
    -0.44
    bootstrapcdn
    -0.44
    printStackTrace
    -0.43
    POSITIVE LOGITS
    ArrowToggle
    0.68
    AsUp
    0.65
     defaultstate
    0.61
    PMailer
    0.61
    dueDate
    0.59
    存于互联网档案馆
    0.56
     Nauka
    0.56
    ticle
    0.56
    nologue
    0.54
    tifies
    0.52
    Activations Density 0.059%

    No Known Activations