© 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. 93921
    Prev
    Next
    INDEX
    Explanations

    study

    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
     study
    -3.23
    study
    -2.88
     Study
    -2.78
    Study
    -2.77
     STUDY
    -2.64
    STUDY
    -2.34
     estudo
    -2.17
     estudio
    -2.16
     studies
    -2.03
     studying
    -1.99
    POSITIVE LOGITS
     of
    0.66
     disambiguazione
    0.61
     by
    0.55
     on
    0.51
    ądź
    0.51
    PRNewswire
    0.50
    ,
    0.49
     that
    0.49
    bnf
    0.48
     involving
    0.47
    Activations Density 1.666%

    No Known Activations