© 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. 92695
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
     HttpHeaders
    -0.69
    ConstraintMaker
    -0.65
    HtmlAttribute
    -0.62
     QWidget
    -0.60
     autorytatywna
    -0.59
    GOTREF
    -0.57
     setTime
    -0.56
     مرئيه
    -0.56
     <<<<<<<<<<<<<<
    -0.55
     belong
    -0.54
    POSITIVE LOGITS
     is
    0.52
     caused
    0.50
     triggered
    0.50
     causado
    0.49
    tadır
    0.49
     samlet
    0.47
     sparked
    0.46
    kuuta
    0.45
     gedaan
    0.45
     lenker
    0.45
    Activations Density 0.001%

    No Known Activations