© 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. 4-CLT-HP
    7. 519
    Prev
    Next
    INDEX
    Explanations

    Questions/Answers/Arguments

    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
     nakalista
    -0.75
    Odkazy
    -0.67
     Gaut
    -0.65
    ConstraintMaker
    -0.64
     تضيفلها
    -0.64
    BeginContext
    -0.63
    ValueStyle
    -0.62
    原始内容存档于
    -0.60
     ويكيميديا
    -0.60
    WriteBarrier
    -0.59
    POSITIVE LOGITS
    tagHelperRunner
    0.70
    IsMutable
    0.52
    Personensuche
    0.50
    cheiben
    0.47
     dicendo
    0.43
     pertanto
    0.43
    бливості
    0.42
     perciò
    0.42
     eccell
    0.42
     oprot
    0.42
    Activations Density 0.065%

    No Known Activations