© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2026
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    érêt
    -0.60
    atterns
    -0.59
    jspb
    -0.58
     defStyle
    -0.58
     chaves
    -0.57
    الحياه
    -0.57
     EconPapers
    -0.57
    adə
    -0.56
    licenses
    -0.55
     utenti
    -0.55
    POSITIVE LOGITS
     Active
    0.45
    ртка
    0.43
    )))
    
    0.43
    MLLoader
    0.43
    `"
    0.41
     "
    
    0.41
    )+"
    0.41
     "
    0.41
     Espa
    0.41
     Questi
    0.41
    Activations Density 0.004%

    No Known Activations