© 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. 94681
    Prev
    Next
    INDEX
    Explanations

    implementation

    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
    Kjelder
    -0.64
    Референце
    -0.63
    featureID
    -0.63
    nloa
    -0.57
     Signalez
    -0.56
     exemples
    -0.55
    تقاوى
    -0.54
     bijvoorbeeld
    -0.54
     hubiera
    -0.52
    saraba
    -0.52
    POSITIVE LOGITS
    ValueStyle
    0.67
     оригіналу
    0.61
    bito
    0.60
    MessageInfo
    0.57
     mainly
    0.57
    ыгана
    0.57
     apparently
    0.56
    awaiter
    0.54
     Apparently
    0.54
     primarily
    0.53
    Activations Density 0.003%

    No Known Activations