© 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. 4533
    Prev
    Next
    INDEX
    Explanations

    technology

    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
     مرئيه
    -0.77
     Мексичка
    -0.77
     OFDb
    -0.75
    GEBURTSDATUM
    -0.75
     فريبيس
    -0.73
     الحره
    -0.71
     виправивши
    -0.71
    apunov
    -0.70
    Билгалдахарш
    -0.70
    +#+#
    -0.70
    POSITIVE LOGITS
     
    0.60
    2
    0.51
    5
    0.48
    3
    0.47
    x
    0.44
    Substituting
    0.44
    BeginInit
    0.43
    <b>
    0.43
    1
    0.43
     solid
    0.43
    Activations Density 0.433%

    No Known Activations