© 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. 92135
    Prev
    Next
    INDEX
    Explanations

    programming/abbreviations

    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
     dal
    -0.58
     az
    -0.57
     van
    -0.54
     South
    -0.54
     menu
    -0.52
     Fort
    -0.52
     Gu
    -0.51
     lot
    -0.51
    bitField
    -0.50
     file
    -0.49
    POSITIVE LOGITS
     Majefty
    0.88
     itſelf
    0.87
     purpoſe
    0.86
     Monfieur
    0.85
     themſelves
    0.77
     ſtate
    0.74
     Houſe
    0.73
     Theſe
    0.71
     démission
    0.70
     Cæsar
    0.69
    Activations Density 0.223%

    No Known Activations