© 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. 0-CLT-HP
    7. 97324
    Prev
    Next
    INDEX
    Explanations

    tro

    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
     FMS
    -0.66
     FCS
    -0.64
     Pharisees
    -0.64
     Hild
    -0.64
     quarries
    -0.63
     biographies
    -0.63
     bibliographies
    -0.63
     diversions
    -0.63
     shields
    -0.62
     Sable
    -0.62
    POSITIVE LOGITS
     présidenti
    0.72
     fraî
    0.69
     nélk
    0.66
     épais
    0.64
     chré
    0.63
     automatiques
    0.63
     préférence
    0.62
     hidrá
    0.60
     dieux
    0.60
     élas
    0.60
    Activations Density 0.022%

    No Known Activations