© 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. 5-CLT-HP
    7. 91069
    Prev
    Next
    INDEX
    Explanations

    one

    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
    Negative Logits
    הערות
    -0.48
    brida
    -0.47
     you
    -0.42
    }{*}{}
    -0.42
    quelle
    -0.41
     your
    -0.41
     anyway
    -0.41
     sports
    -0.40
    rensen
    -0.40
    ishin
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.77
     propOrder
    0.75
     pinulongan
    0.65
    WriteAttribute
    0.64
    portlet
    0.64
     considérons
    0.63
    GEBURTS
    0.63
    Tikang
    0.62
     resourceCulture
    0.61
    NamedQuery
    0.60
    Activations Density 0.045%

    No Known Activations