© 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. 6237
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    TypedDataSet
    -0.65
    Personendaten
    -0.64
    ējās
    -0.63
    WindowConstants
    -0.63
    modelBuilder
    -0.61
    ReusableCell
    -0.57
     možno
    -0.55
    expandindo
    -0.54
    antasy
    -0.54
    Portail
    -0.54
    POSITIVE LOGITS
     BoxDecoration
    0.53
    opsida
    0.52
    AfterClass
    0.52
     >=",
    0.51
     '\\;'
    0.50
    cang
    0.49
     getRule
    0.48
     McCra
    0.47
    anyaan
    0.46
     Ball
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.