© 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. 8701
    Prev
    Next
    INDEX
    Explanations

    technical/science text

    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
    ʃ
    -0.78
     CreateTagHelper
    -0.68
     propOrder
    -0.66
     betweenstory
    -0.63
     initComponents
    -0.63
    ʒ
    -0.62
    Erreferentziak
    -0.62
     utafitiHapana
    -0.60
    Externí
    -0.59
     Hartman
    -0.59
    POSITIVE LOGITS
    HasForeignKey
    0.58
    GenerationType
    0.51
    DebuggerNonUser
    0.47
     poveznice
    0.47
    jestel
    0.47
    ListModule
    0.47
    WireFormat
    0.46
     gewi
    0.45
    WireFormatLite
    0.44
    ContentLoaded
    0.44
    Activations Density 0.030%

    No Known Activations