© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4237
    Prev
    Next
    INDEX
    Explanations

    academic/scientific writing

    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
     Мексичка
    -0.85
    Personendaten
    -0.83
     autorytatywna
    -0.78
    parsedMessage
    -0.74
    ItemBackground
    -0.74
    Personensuche
    -0.73
    tonode
    -0.71
     resourceCulture
    -0.70
    Sucesor
    -0.68
    بوابة
    -0.67
    POSITIVE LOGITS
     giustizia
    0.52
    dolu
    0.50
    any
    0.49
     varandra
    0.49
     terapé
    0.47
     the
    0.46
     santé
    0.46
     any
    0.45
     Vermögen
    0.45
    ficación
    0.45
    Activations Density 0.005%

    No Known Activations