© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8986
    Prev
    Next
    INDEX
    Explanations

    protection

    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
    RegressionTest
    -0.60
     protected
    -0.58
    protected
    -0.57
    PROTECT
    -0.52
    LookAnd
    -0.52
    AnchorTagHelper
    -0.50
     protecting
    -0.50
     protection
    -0.50
     protéger
    -0.48
    保護
    -0.47
    POSITIVE LOGITS
     Saras
    0.68
     myſelf
    0.68
    KommentareTeilen
    0.65
     raiſ
    0.64
    énéral
    0.63
     faſt
    0.62
     toJson
    0.61
    ện
    0.60
     ſy
    0.59
     poffible
    0.59
    Activations Density 0.023%

    No Known Activations