© 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. 39787
    Prev
    Next
    INDEX
    Explanations

    large-scale operations/debates/studies

    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
     Efq
    -0.84
     varandra
    -0.75
     Monfieur
    -0.73
     ſche
    -0.72
     ſeveral
    -0.70
     Shakspeare
    -0.68
     reaſon
    -0.68
     Eſ
    -0.67
     وتسجيلات
    -0.66
     purpoſe
    -0.65
    POSITIVE LOGITS
     autorytatywna
    0.60
     viewDidLoad
    0.52
    findpost
    0.50
     lanjut
    0.50
    AHN
    0.49
     fan
    0.48
    landt
    0.48
    manjaro
    0.47
    thalene
    0.47
    tonode
    0.47
    Activations Density 0.093%

    No Known Activations