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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9509
    Prev
    Next
    INDEX
    Explanations

    words and text analysis

    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
     words
    -0.85
     WORDS
    -0.76
    ViewFeatures
    -0.69
     ویکی‌پدیا
    -0.68
    reservations
    -0.67
     thorns
    -0.65
     adjectives
    -0.64
     word
    -0.63
    CodedInputStream
    -0.62
    +:+
    -0.61
    POSITIVE LOGITS
     devoirs
    0.48
     internetowa
    0.47
     preuves
    0.46
     vaisseaux
    0.45
     supérieures
    0.45
     biens
    0.45
     gouvernements
    0.45
    ızlık
    0.44
     legais
    0.43
     navires
    0.43
    Activations Density 0.015%

    No Known Activations