© 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. 44041
    Prev
    Next
    INDEX
    Explanations

    animals and the brain

    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
     Monfieur
    -1.10
     itſelf
    -1.09
     photolibrary
    -1.01
     myſelf
    -1.00
     faſt
    -0.98
     Anſ
    -0.96
     Efq
    -0.94
     poffe
    -0.93
     himſelf
    -0.91
     fédé
    -0.90
    POSITIVE LOGITS
    ep
    0.53
    e
    0.53
    ele
    0.50
    :+:
    0.50
    ee
    0.49
     Fer
    0.48
     The
    0.48
     co
    0.47
    <eos>
    0.46
     I
    0.45
    Activations Density 1.645%

    No Known Activations