© 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. 4-CLT-HP
    7. 3184
    Prev
    Next
    INDEX
    Explanations

    save

    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
     AspNetCore
    -0.67
     ayudarte
    -0.50
     démocr
    -0.49
     ayudado
    -0.48
    bbene
    -0.43
     dispuestos
    -0.43
     preocu
    -0.42
     ulang
    -0.42
     remedied
    -0.42
     dilakukan
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.83
    copg
    0.68
    MessageTagHelper
    0.67
    +:+
    0.62
    iler
    0.60
     EconPapers
    0.59
     life
    0.59
    ftagPool
    0.58
     CYTHON
    0.58
     what
    0.58
    Activations Density 0.003%

    No Known Activations