© 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. 90803
    Prev
    Next
    INDEX
    Explanations

    s

    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
    ukone
    -0.73
    kháu
    -0.71
    TintMode
    -0.71
     Baillargeon
    -0.68
     entanto
    -0.66
     pravi
    -0.60
     betweenstory
    -0.60
     itſelf
    -0.60
     мәкал
    -0.60
    Хьажоргаш
    -0.59
    POSITIVE LOGITS
     a
    1.15
     not
    1.11
     an
    1.07
     the
    0.93
     also
    0.86
     able
    0.77
     probably
    0.73
     definitely
    0.71
     been
    0.70
     both
    0.69
    Activations Density 0.195%

    No Known Activations