Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44903
    Prev
    Next
    INDEX
    Explanations

    yen

    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
     EV
    -0.75
    roek
    -0.69
    ness
    -0.64
     fVar
    -0.60
    ️
    -0.60
     Telerik
    -0.57
    তথ্যসূত্র
    -0.57
    cillor
    -0.55
     виправивши
    -0.55
    enite
    -0.54
    POSITIVE LOGITS
     purpoſe
    0.77
     Jefus
    0.75
     chofe
    0.68
     Chriſt
    0.65
     Majefty
    0.65
     Monfieur
    0.65
     Chriftian
    0.64
     uſed
    0.63
     myſelf
    0.63
     Hift
    0.63
    Activations Density 0.062%

    No Known Activations