© 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. 0-CLT-HP
    7. 42853
    Prev
    Next
    INDEX
    Explanations

    induced

    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
     induced
    -0.74
    Erreferentziak
    -0.73
     CreateTagHelper
    -0.73
     acute
    -0.71
    Acute
    -0.67
    Induced
    -0.65
     Induced
    -0.64
    acute
    -0.63
     equivalent
    -0.63
    astify
    -0.62
    POSITIVE LOGITS
    ly
    0.88
    s
    0.69
    LY
    0.54
     plaques
    0.52
     EconPapers
    0.50
    DIPSETTING
    0.48
     Pla
    0.46
     Successfully
    0.46
     Drill
    0.45
     Hege
    0.45
    Activations Density 0.091%

    No Known Activations