© 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. 0-CLT-HP
    7. 92669
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
     NSCoder
    -0.99
     disambiguazione
    -0.98
    Gambas
    -0.97
    oneofs
    -0.95
     tartalomajánló
    -0.92
    kháu
    -0.90
    تقاوى
    -0.89
    endphp
    -0.88
    OGND
    -0.87
     незавершена
    -0.87
    POSITIVE LOGITS
    ing
    0.50
     phase
    0.46
     expansion
    0.45
    िज
    0.45
     J
    0.45
     of
    0.44
     real
    0.44
    ,
    0.44
    es
    0.43
    ën
    0.43
    Activations Density 0.126%

    No Known Activations