© 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. 5-CLT-HP
    7. 4722
    Prev
    Next
    INDEX
    Explanations

    continue

    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
    didSet
    -0.74
     незавершена
    -0.63
    IsMutable
    -0.57
    دانشنامهٔ
    -0.55
    Rüyada
    -0.51
    :✨
    -0.51
    发表于
    -0.51
    GEBURTSDATUM
    -0.50
    UnsafeEnabled
    -0.50
    BeginContext
    -0.50
    POSITIVE LOGITS
    />";
    0.62
     <>",
    0.57
    ècie
    0.56
    >");
    0.54
    tidaknya
    0.52
    off
    0.52
    )++;
    0.51
    ."],
    0.50
    new
    0.50
    '>"
    0.50
    Activations Density 0.001%

    No Known Activations