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. 44445
    Prev
    Next
    INDEX
    Explanations

    isinin

    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
    ly
    -0.81
    er
    -0.63
    ième
    -0.56
    o
    -0.54
     reportedly
    -0.52
    a
    -0.51
    aisons
    -0.48
     Walkover
    -0.47
     tight
    -0.46
    pédie
    -0.46
    POSITIVE LOGITS
     myſelf
    1.38
     Efq
    1.35
     Theſe
    1.32
     Diſ
    1.30
     Monfieur
    1.27
     Jefus
    1.27
     houſe
    1.25
     themſelves
    1.24
     uſe
    1.23
     Anſ
    1.23
    Activations Density 0.120%

    No Known Activations