© 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. 12959
    Prev
    Next
    INDEX
    Explanations

    Orchestral

    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
    al
    -1.30
    AL
    -0.80
    altes
    -0.65
    almo
    -0.64
    alni
    -0.57
     Initialized
    -0.57
     al
    -0.56
     Neurol
    -0.56
    alna
    -0.56
    alm
    -0.55
    POSITIVE LOGITS
    queryInterface
    0.56
    contentLoaded
    0.45
     commerciales
    0.45
    scrapy
    0.43
    tagHelperRunner
    0.42
     trás
    0.41
    bitat
    0.41
    зраст
    0.41
    AutoScale
    0.40
    }]
    0.40
    Activations Density 0.034%

    No Known Activations