© 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. 1-CLT-HP
    7. 14386
    Prev
    Next
    INDEX
    Explanations

    and

    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
     BoxFit
    -0.63
    !*\
    -0.62
     يتيمه
    -0.62
     transfieras
    -0.61
     Neighbors
    -0.59
     Favorite
    -0.59
    ftagPool
    -0.58
    behavioral
    -0.57
     Fiber
    -0.56
     Neighborhood
    -0.56
    POSITIVE LOGITS
    ViewImports
    0.59
     autorytatywna
    0.53
    Kjelder
    0.50
    dibles
    0.49
    RegressionTest
    0.47
     Küste
    0.47
    saurus
    0.46
    ESTONE
    0.46
     folgt
    0.45
     vastaan
    0.45
    Activations Density 0.012%

    No Known Activations