© 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. 9097
    Prev
    Next
    INDEX
    Explanations

    derivative

    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
    RegressionTest
    -0.73
    ergies
    -0.69
    elemField
    -0.63
    }{*}{}
    -0.63
    quelize
    -0.60
    GEBURTSDATUM
    -0.60
    glLoadIdentity
    -0.59
     BoxFit
    -0.59
     estimés
    -0.59
    adel
    -0.58
    POSITIVE LOGITS
    CppMethod
    0.51
    sm
    0.49
     chi̍t
    0.46
    series
    0.44
     dentaire
    0.42
    endront
    0.42
     époque
    0.42
     espont
    0.41
     AssemblyCompany
    0.41
    sok
    0.40
    Activations Density 0.060%

    No Known Activations