© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 206
    Prev
    Next
    INDEX
    Explanations

    resize

    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
    ⓧ
    -0.61
     StatelessWidget
    -0.59
    macht
    -0.57
     StatefulWidget
    -0.56
     NSCoder
    -0.55
    BeginContext
    -0.55
    setVerticalGroup
    -0.55
    nodoc
    -0.49
    świet
    -0.49
     AppComponent
    -0.48
    POSITIVE LOGITS
     Roskov
    0.66
    logique
    0.53
     wards
    0.48
     ivelany
    0.48
     noDo
    0.48
    guarded
    0.47
     canoes
    0.47
     Obr
    0.47
     Autorizaciones
    0.46
     Hivatalos
    0.46
    Activations Density 0.004%

    No Known Activations