© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12406
    Prev
    Next
    INDEX
    Explanations

    predis

    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
    SourceChecksum
    -0.66
    Rüyada
    -0.65
     الحره
    -0.63
    ChromeDriver
    -0.60
    はじめに
    -0.57
    RunWith
    -0.56
    WebVitals
    -0.53
    ChildScrollView
    -0.52
    #+#
    -0.52
    ///</
    -0.52
    POSITIVE LOGITS
     gesetzt
    0.55
    parin
    0.50
    pose
    0.50
    posing
    0.50
    ccione
    0.49
    ptonshire
    0.49
     Савез
    0.47
    posed
    0.47
    titleMargin
    0.47
    sesion
    0.46
    Activations Density 0.066%

    No Known Activations