© 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. 4-CLT-HP
    7. 933
    Prev
    Next
    INDEX
    Explanations

    renal

    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
    حياتها
    -0.63
    حياته
    -0.61
     ProtoMessage
    -0.57
     Wikimedijinoj
    -0.56
     Egg
    -0.56
    Egg
    -0.54
    Speed
    -0.50
    سک
    -0.50
     eggs
    -0.50
    Guards
    -0.50
    POSITIVE LOGITS
    ThroughAttribute
    0.77
     CreateTagHelper
    0.77
    tagHelperRunner
    0.69
    setVerticalGroup
    0.67
     <=",
    0.54
    RegressionTest
    0.53
    ofire
    0.53
     ब्रेकडाउन
    0.51
    enderror
    0.51
    yntaxException
    0.50
    Activations Density 0.001%

    No Known Activations