© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96658
    Prev
    Next
    INDEX
    Explanations

    initiatives, attempts, efforts

    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
    спонд
    -0.54
    expandindo
    -0.52
    Референце
    -0.50
     tartalomajánló
    -0.45
    roskop
    -0.43
     Wrote
    -0.43
    неопр
    -0.43
    ędziesz
    -0.42
     wrote
    -0.42
    oga
    -0.41
    POSITIVE LOGITS
     by
    1.08
     oleh
    0.83
    contentLoaded
    0.68
    
    0.66
    سطس
    0.65
    phosa
    0.60
     توسط
    0.59
     ידי
    0.58
    quisa
    0.57
     الحره
    0.57
    Activations Density 0.000%

    No Known Activations