© 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. 1-CLT-HP
    7. 357
    Prev
    Next
    INDEX
    Explanations

    countries and nationalities

    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
     run
    -0.43
     water
    -0.41
     ode
    -0.40
    apo
    -0.40
    ovic
    -0.39
     complex
    -0.39
     particular
    -0.39
     prin
    -0.38
     Sans
    -0.38
     heir
    -0.38
    POSITIVE LOGITS
    rungsseite
    1.05
    bewerken
    0.90
     AssemblyCulture
    0.85
     nahilalakip
    0.84
    BeginInit
    0.84
    Vidite
    0.82
    IndentedString
    0.82
    mybatisplus
    0.82
     ivelany
    0.82
     <>",
    0.82
    Activations Density 0.003%

    No Known Activations