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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45664
    Prev
    Next
    INDEX
    Explanations

    solid

    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
     مشين
    -0.55
     besök
    -0.54
    AntiForgeryToken
    -0.54
     químicas
    -0.54
    Plates
    -0.52
    createComponent
    -0.52
     Winfrey
    -0.52
    Doctors
    -0.51
    plate
    -0.50
    AutoScaleMode
    -0.50
    POSITIVE LOGITS
     Vort
    0.57
     Earth
    0.57
     transfieras
    0.56
     Fitz
    0.51
     earth
    0.51
    NameInMap
    0.50
     Observable
    0.50
    tvguidetime
    0.48
     typelib
    0.48
    Obrázky
    0.48
    Activations Density 0.024%

    No Known Activations