© 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. 5-CLT-HP
    7. 96104
    Prev
    Next
    INDEX
    Explanations

    technical answers/solutions

    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
    bani
    -0.47
    asten
    -0.46
     ú
    -0.46
    anius
    -0.45
     sc
    -0.44
    atikan
    -0.44
    tin
    -0.43
     
    -0.43
     above
    -0.43
     }>
    -0.43
    POSITIVE LOGITS
    клопе
    0.74
     Daß
    0.70
     ainfi
    0.65
    StoryboardSegue
    0.63
     uſed
    0.63
    RegistryLite
    0.61
     químicas
    0.61
    seamnă
    0.60
     Efq
    0.60
    openConnection
    0.59
    Activations Density 0.000%

    No Known Activations