© 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. 93364
    Prev
    Next
    INDEX
    Explanations

    now

    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
    EDEFAULT
    -0.57
    ÁG
    -0.55
     now
    -0.54
     <=",
    -0.52
    ÉR
    -0.52
    ValueGenerated
    -0.50
    ńcz
    -0.50
    clickOn
    -0.50
    enoch
    -0.49
    essica
    -0.49
    POSITIVE LOGITS
     nationaux
    0.56
     comiendo
    0.53
     actifs
    0.51
     artesanales
    0.50
     scolaires
    0.50
     démocr
    0.50
     ativos
    0.49
    GEBURTSDATUM
    0.49
     chré
    0.48
     gambe
    0.48
    Activations Density 0.002%

    No Known Activations