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. 5-CLT-HP
    4. 1515
    Prev
    Next
    INDEX
    Explanations

    Scientific, organizational text

    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
     «
    -0.45
    cgi
    -0.43
    }}=$
    -0.41
     '
    -0.40
     g
    -0.39
     Table
    -0.38
     ही
    -0.38
     X
    -0.38
     tia
    -0.38
     Il
    -0.38
    POSITIVE LOGITS
     Shakspeare
    0.91
     betweenstory
    0.80
     CURIAM
    0.80
     Mahomet
    0.77
     holotype
    0.77
     purpoſe
    0.77
     pleaſure
    0.77
     perſon
    0.73
     reaſon
    0.73
     itſelf
    0.72
    Activations Density 0.040%

    No Known Activations