© 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. 1-CLT-HP
    7. 14607
    Prev
    Next
    INDEX
    Explanations

    negative situations/words

    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
    ifiable
    -0.70
    ensible
    -0.63
    angler
    -0.59
    aboo
    -0.56
     Akismet
    -0.54
     extensible
    -0.52
     ویکی‌پدیا
    -0.51
    pies
    -0.50
    umman
    -0.50
     Crunch
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.56
    fromnode
    0.54
    findpost
    0.54
     GenerationType
    0.49
    IBarButtonItem
    0.47
    HasAnnotation
    0.46
    hassee
    0.46
    InjectAttribute
    0.46
    Specifiche
    0.45
     initComponents
    0.45
    Activations Density 0.008%

    No Known Activations