© 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. 94775
    Prev
    Next
    INDEX
    Explanations

    ru

    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
     препратки
    -0.61
     ویکی‌پدیا
    -0.58
    san
    -0.57
    AttributeSet
    -0.57
    VersionUID
    -0.55
    \{\\
    -0.55
     BoxDecoration
    -0.54
    AutoScaleMode
    -0.54
     Wikiseite
    -0.52
     оригіналу
    -0.51
    POSITIVE LOGITS
    latimes
    0.48
    weile
    0.48
     banget
    0.47
     gambe
    0.47
    ρεύ
    0.47
    omic
    0.47
     chain
    0.46
    oto
    0.46
     Chain
    0.45
    ocrats
    0.45
    Activations Density 0.002%

    No Known Activations