© 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. 6072
    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
    RectangleBorder
    -0.76
     myſelf
    -0.71
     Cze
    -0.71
     becauſe
    -0.68
     itſelf
    -0.68
     sähkö
    -0.68
    ISupport
    -0.68
     Jefus
    -0.66
     Efq
    -0.64
     ſche
    -0.64
    POSITIVE LOGITS
     initComponents
    0.77
    WireFormat
    0.54
     Show
    0.53
    matchCondition
    0.52
     ISNI
    0.51
    सन्दर्भ
    0.51
     show
    0.50
     given
    0.49
    ยะ
    0.49
    zug
    0.48
    Activations Density 0.029%

    No Known Activations