© 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. 4-CLT-HP
    7. 4774
    Prev
    Next
    INDEX
    Explanations

    this

    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
    .
    -0.49
     além
    -0.47
     utilizando
    -0.46
    according
    -0.46
    while
    -0.46
     are
    -0.44
     utilizzando
    -0.44
    without
    -0.44
     através
    -0.43
    ствую
    -0.43
    POSITIVE LOGITS
     CURIAM
    0.73
    SequentialGroup
    0.66
     חיצוניים
    0.65
     intptr
    0.64
     newly
    0.64
    NewLabel
    0.61
     new
    0.60
    atify
    0.60
    ArrowToggle
    0.59
     EconPapers
    0.57
    Activations Density 0.008%

    No Known Activations