© 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. 43352
    Prev
    Next
    INDEX
    Explanations

    correctly/appropriately

    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
     correctly
    -1.23
     properly
    -1.20
    properly
    -1.13
     appropriately
    -1.11
     correctement
    -1.08
     Properly
    -1.04
     rightly
    -1.01
    aarrggbb
    -0.96
    correctly
    -0.96
     accurately
    -0.86
    POSITIVE LOGITS
     XCTest
    0.53
    itemBuilder
    0.47
    fp
    0.47
     clustered
    0.46
    ács
    0.45
     void
    0.45
     bổ
    0.45
    ViewImports
    0.45
    AttributeSet
    0.44
    ActionCreators
    0.44
    Activations Density 0.036%

    No Known Activations