Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39020
    Prev
    Next
    INDEX
    Explanations

    code or legal documents

    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
    arithmic
    -0.63
    HasAnnotation
    -0.62
     متعلقه
    -0.61
    Tembelea
    -0.58
    AlterField
    -0.57
    .*")]
    -0.57
     IOError
    -0.57
    oa̍t
    -0.56
    IsMutable
    -0.56
    soort
    -0.53
    POSITIVE LOGITS
    Према
    0.56
     виправивши
    0.55
    brenner
    0.52
     تضيفلها
    0.51
    Xk
    0.50
    Viitteet
    0.49
    ínia
    0.46
    com
    0.45
    Dec
    0.45
    mirror
    0.45
    Activations Density 1.658%

    No Known Activations