© 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. 91040
    Prev
    Next
    INDEX
    Explanations

    biographical texts

    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
     developmental
    -0.36
     growth
    -0.35
     development
    -0.35
     remarked
    -0.33
     treatments
    -0.32
     therap
    -0.32
     paints
    -0.31
    %=
    -0.31
     magasiner
    -0.31
     treatment
    -0.30
    POSITIVE LOGITS
    featureID
    0.79
    CloseOperation
    0.79
    TestingModule
    0.76
    Rüyada
    0.71
    sizeCache
    0.69
    SourceChecksum
    0.69
     مواليد
    0.69
    SpringBootTest
    0.69
    BibitemShut
    0.69
    terness
    0.68
    Activations Density 0.000%

    No Known Activations