© 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. 91178
    Prev
    Next
    INDEX
    Explanations

    competent

    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
    Personensuche
    -0.94
     ModelExpression
    -0.93
    
    -0.92
     AssemblyCompany
    -0.89
     <=",
    -0.88
    :✨
    -0.84
    حوالہ
    -0.84
     AssemblyCulture
    -0.83
     endforeach
    -0.83
     AssemblyProduct
    -0.83
    POSITIVE LOGITS
    ulated
    0.48
    ated
    0.47
     to
    0.46
     Pedro
    0.45
    alha
    0.44
    ّا
    0.44
    ALES
    0.43
    tsu
    0.42
    naco
    0.42
    maru
    0.41
    Activations Density 0.061%

    No Known Activations