© 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. 5-CLT-HP
    7. 5576
    Prev
    Next
    INDEX
    Explanations

    the

    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
     memorized
    -0.65
    WriteTagHelper
    -0.65
    ConstraintMaker
    -0.64
    TagMode
    -0.63
     memorize
    -0.59
    contentLoaded
    -0.54
    accumulative
    -0.53
    RegressionTest
    -0.52
     AssemblyVersion
    -0.51
     transférez
    -0.51
    POSITIVE LOGITS
    ][:
    0.62
    /**
    0.60
    Collegamenti
    0.59
     Paglinawan
    0.52
    prüche
    0.47
    uela
    0.47
    ìa
    0.47
    pol
    0.47
    дарь
    0.47
    hb
    0.47
    Activations Density 0.001%

    No Known Activations