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. 91482
    Prev
    Next
    INDEX
    Explanations

    packets

    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
     virginity
    -0.84
    rungsseite
    -0.82
     eruptions
    -0.82
     alternation
    -0.82
     emigration
    -0.80
     eruption
    -0.79
     rituals
    -0.78
     precincts
    -0.78
     prophecies
    -0.77
     constitutions
    -0.77
    POSITIVE LOGITS
    tead
    0.53
     and
    0.53
     per
    0.52
    capes
    0.51
     over
    0.50
    ensitive
    0.50
    heds
    0.50
    cape
    0.48
    ystems
    0.47
    creen
    0.47
    Activations Density 0.060%

    No Known Activations