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. 44556
    Prev
    Next
    INDEX
    Explanations

    Dump

    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
     varandra
    -0.93
     dieux
    -0.92
     démocr
    -0.91
     enfans
    -0.88
     igång
    -0.88
     fermés
    -0.88
     stället
    -0.88
     avoient
    -0.86
     étoient
    -0.85
     normaux
    -0.83
    POSITIVE LOGITS
    <bos>
    0.83
     the
    0.61
    -
    0.55
    ↵↵
    0.53
     a
    0.52
    an
    0.52
    st
    0.51
     about
    0.50
     and
    0.50
     well
    0.50
    Activations Density 0.093%

    No Known Activations