© 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. 45192
    Prev
    Next
    INDEX
    Explanations

    result

    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
     derniers
    -0.59
     ultimi
    -0.58
     dernière
    -0.55
     last
    -0.54
     förra
    -0.52
     últimas
    -0.51
     rentrée
    -0.51
     terakhir
    -0.50
     dernières
    -0.49
     últimos
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.86
     itſelf
    0.81
    Portail
    0.79
     ExecuteAsync
    0.77
     Signalez
    0.76
     Rwand
    0.73
     ſtre
    0.73
     pleaſure
    0.72
     Peruvian
    0.71
     незавершена
    0.71
    Activations Density 0.147%

    No Known Activations