© 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. 44055
    Prev
    Next
    INDEX
    Explanations

    Spanish

    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
    NamedQueries
    -0.61
     שוליים
    -0.59
    twimg
    -0.54
    ourites
    -0.53
    cipline
    -0.52
     gynhyrchwyd
    -0.50
    hilation
    -0.49
    Caster
    -0.48
    ricated
    -0.47
    terscotch
    -0.47
    POSITIVE LOGITS
    contentLoaded
    0.61
    harusnya
    0.57
    出版年
    0.57
    dtd
    0.53
    .*")]
    0.52
    хіво
    0.51
    readline
    0.50
     uska
    0.50
    γγε
    0.50
    BeginInit
    0.50
    Activations Density 0.059%

    No Known Activations