© 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. 39873
    Prev
    Next
    INDEX
    Explanations

    Diverse news snippets

    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
     speciale
    -0.62
     spéciale
    -0.61
     spéciaux
    -0.57
     especiales
    -0.56
    ğunu
    -0.50
    之一
    -0.46
    but
    -0.46
     особли
    -0.46
     спеціаль
    -0.45
    ity
    -0.44
    POSITIVE LOGITS
    ResumeLayout
    1.04
    ]--;
    0.81
    expandindo
    0.80
     tartalomajánló
    0.79
    ValueStyle
    0.78
     defaultstate
    0.77
    MethodManager
    0.77
    ]<<"
    0.75
     Majefty
    0.73
    KommentareTeilen
    0.73
    Activations Density 0.160%

    No Known Activations