© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44119
    Prev
    Next
    INDEX
    Explanations

    un

    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
     un
    -1.47
     who
    -0.98
     uns
    -0.82
     Un
    -0.81
     unt
    -0.75
     ung
    -0.66
     una
    -0.66
    who
    -0.65
     non
    -0.61
     a
    -0.60
    POSITIVE LOGITS
     bénéfices
    0.83
     hiperten
    0.67
     renseignements
    0.66
    TintMode
    0.65
     étoient
    0.65
     investissements
    0.62
     suivez
    0.62
     cérami
    0.61
     parlent
    0.61
     تكبرها
    0.61
    Activations Density 0.126%

    No Known Activations