© 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. 38889
    Prev
    Next
    INDEX
    Explanations

    Five

    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
     One
    -1.23
     Five
    -1.14
     Two
    -1.09
     Three
    -1.07
     Eight
    -1.05
    One
    -1.02
    Five
    -0.93
     Four
    -0.91
     Six
    -0.88
     Sixteen
    -0.87
    POSITIVE LOGITS
     Ways
    0.62
     or
    0.61
     of
    0.59
    -
    0.59
     more
    0.56
     other
    0.54
     way
    0.54
     Way
    0.53
    <eos>
    0.52
     hundred
    0.52
    Activations Density 0.138%

    No Known Activations