© 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. 10181
    Prev
    Next
    INDEX
    Explanations

    employment

    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
    emploi
    -0.54
     persoalan
    -0.49
     Employment
    -0.49
    drück
    -0.48
     باخ
    -0.47
    llingwood
    -0.46
    värr
    -0.46
     inmediato
    -0.45
    ziplin
    -0.45
     censi
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.77
    出版年
    0.71
    ########.
    0.71
     chi̍t
    0.64
    InSection
    0.64
    ⓧ
    0.61
    .";
    0.60
    SuppressMessage
    0.59
     Pent
    0.56
    astify
    0.56
    Activations Density 0.026%

    No Known Activations