© 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. 90760
    Prev
    Next
    INDEX
    Explanations

    Words starting with Dra/Scra/Sle/Cra

    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
    ArgsConstructor
    -0.72
    ⓧ
    -0.60
     Opposition
    -0.59
     fact
    -0.57
     Lib
    -0.57
    InjectMocks
    -0.56
     Sle
    -0.56
    ن
    -0.56
    neu
    -0.55
    引
    -0.54
    POSITIVE LOGITS
     espirituales
    0.63
     souffrance
    0.55
    InjectAttribute
    0.54
    pped
    0.52
     fidèles
    0.51
     aikaa
    0.50
     inteligentes
    0.50
     destrucción
    0.50
     الرياضيه
    0.49
     écou
    0.48
    Activations Density 1.035%

    No Known Activations