© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90991
    Prev
    Next
    INDEX
    Explanations

    technical articles

    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
     healthy
    -0.96
    Healthy
    -0.76
     équilibr
    -0.70
    healthy
    -0.67
     gesunde
    -0.65
     Healthy
    -0.65
     buy
    -0.64
     medium
    -0.59
    buy
    -0.59
    ArgumentParser
    -0.59
    POSITIVE LOGITS
    StructEnd
    0.93
    <bos>
    0.79
     betweenstory
    0.70
    Diwedd
    0.69
     unknownFields
    0.64
    crollView
    0.64
     defaultstate
    0.63
    cense
    0.63
     Koran
    0.62
    ItemBackground
    0.60
    Activations Density 0.246%

    No Known Activations