© 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. 94950
    Prev
    Next
    INDEX
    Explanations

    YY

    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
    mě
    -0.47
     element
    -0.47
    glades
    -0.46
     derivative
    -0.43
    osomal
    -0.42
     invas
    -0.42
     stof
    -0.42
     احترام
    -0.42
    away
    -0.41
    mette
    -0.41
    POSITIVE LOGITS
    fillType
    0.72
    脚注の使い方
    0.68
    Erreferentziak
    0.67
    StoryboardSegue
    0.65
    Tembelea
    0.63
    sizeCache
    0.60
    ########.
    0.60
    ंदीखरीदारी
    0.58
    rungsseite
    0.57
    RTEX
    0.57
    Activations Density 0.002%

    No Known Activations