© 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. 4-CLT-HP
    7. 3232
    Prev
    Next
    INDEX
    Explanations

    inity

    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
     néglig
    -0.52
     résister
    -0.48
     oublier
    -0.47
     fréquent
    -0.46
     preuves
    -0.45
     fermés
    -0.45
     mères
    -0.44
     âmes
    -0.43
     encontra
    -0.43
     accordé
    -0.43
    POSITIVE LOGITS
     reaſon
    1.08
     poffible
    1.03
     Efq
    1.03
     pleaſure
    1.02
     perfons
    1.00
     fubject
    1.00
     myſelf
    0.99
     reafon
    0.98
     ſche
    0.97
     leaſt
    0.96
    Activations Density 0.000%

    No Known Activations