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. 168
    Prev
    Next
    INDEX
    Explanations

    Yankee/catcher

    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
     '
    -1.01
    ↵↵
    -0.97
     "
    -0.96
     
    -0.92
     de
    -0.91
     “
    -0.91
     ‘
    -0.89
     (
    -0.86
     la
    -0.85
     e
    -0.84
    POSITIVE LOGITS
     Efq
    2.55
     myſelf
    2.45
     Monfieur
    2.44
     Majefty
    2.36
     houſe
    2.31
     Reſ
    2.31
     Houſe
    2.31
     ſeveral
    2.31
     itſelf
    2.31
     pleaſure
    2.30
    Activations Density 0.773%

    No Known Activations