© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42242
    Prev
    Next
    INDEX
    Explanations

    opponents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     neighbours
    -1.30
     neighbors
    -1.27
     colleagues
    -1.23
     counterparts
    -1.17
     rivals
    -1.16
     neighbour
    -1.15
     neighbor
    -1.13
     colleague
    -1.13
     peers
    -1.05
     opponents
    -1.01
    POSITIVE LOGITS
     financières
    0.76
     immédi
    0.73
    WithMany
    0.72
    JspWriter
    0.68
     vectorielle
    0.65
     malheure
    0.64
     Jurí
    0.64
    DeleteBehavior
    0.62
     religieuses
    0.59
    IUrlHelper
    0.59
    Activations Density 0.103%

    No Known Activations