© 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. 38720
    Prev
    Next
    INDEX
    Explanations

    app

    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
     app
    -0.73
     App
    -0.66
     clauses
    -0.60
    clause
    -0.60
     clause
    -0.59
    luk
    -0.56
    urably
    -0.52
    存于互联网档案馆
    -0.49
    chey
    -0.48
     Sa
    -0.47
    POSITIVE LOGITS
     itſelf
    0.98
     myſelf
    0.93
     Anſ
    0.86
     uſed
    0.85
     uſe
    0.84
     pleaſure
    0.84
    ſelf
    0.83
     purpoſe
    0.82
     Jefus
    0.82
    ſelves
    0.80
    Activations Density 0.173%

    No Known Activations