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. 5-CLT-HP
    4. 1932
    Prev
    Next
    INDEX
    Explanations

    congratulations

    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
    
    -0.63
    IsContent
    -0.55
    ﷺ
    -0.52
    aspectj
    -0.50
    GETHER
    -0.48
    Revue
    -0.47
    ätzlich
    -0.47
     оригіналу
    -0.46
    tersebut
    -0.46
    omitempty
    -0.45
    POSITIVE LOGITS
    ulatory
    0.69
    RegistryLite
    0.66
    ulating
    0.66
     pinulongan
    0.64
    ulation
    0.62
    ula
    0.57
    ulates
    0.56
    SpringBootTest
    0.56
    tadi
    0.55
    olini
    0.52
    Activations Density 0.003%

    No Known Activations