© 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. 90934
    Prev
    Next
    INDEX
    Explanations

    All

    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
     All
    -2.08
    All
    -1.62
     ALL
    -1.36
     all
    -1.26
    ALL
    -1.07
    all
    -0.85
     Все
    -0.75
     A
    -0.72
     min
    -0.70
    オール
    -0.70
    POSITIVE LOGITS
     Theſe
    1.41
     Houſe
    1.40
     Reſ
    1.39
     Anſ
    1.30
     Efq
    1.29
     Diſ
    1.27
     Majefty
    1.27
     Monfieur
    1.27
     purpoſe
    1.23
     myſelf
    1.22
    Activations Density 0.445%

    No Known Activations