© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92923
    Prev
    Next
    INDEX
    Explanations

    excuse/reason

    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
    ArgsConstructor
    -0.55
    IsMutable
    -0.51
     sementes
    -0.48
     disambiguazione
    -0.48
    TestTools
    -0.47
    ContentLoaded
    -0.47
    AndEndTag
    -0.47
     Normdatei
    -0.47
     cierto
    -0.45
    stretchr
    -0.45
    POSITIVE LOGITS
     why
    0.73
     reasons
    0.71
    Reasons
    0.66
     for
    0.66
    reasons
    0.64
    DebuggerNonUser
    0.62
    REASONS
    0.61
    RegressionTest
    0.59
     ModelExpression
    0.58
     reason
    0.57
    Activations Density 0.005%

    No Known Activations