© 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. 20-CLT-HP
    7. 71272
    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
     Flow
    -0.61
    hila
    -0.57
     flow
    -0.57
    thâu
    -0.54
     Hydrology
    -0.54
    flow
    -0.53
    spre
    -0.53
     flows
    -0.52
     ImportError
    -0.52
    Flow
    -0.51
    POSITIVE LOGITS
    OCCURRED
    0.65
    يميديا
    0.57
     estekak
    0.57
    ValueStyle
    0.54
    PYX
    0.54
     transfieras
    0.53
    GEBURTSDATUM
    0.53
     NSCoder
    0.52
    culadora
    0.51
     propOrder
    0.51
    Activations Density 0.002%

    No Known Activations