© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4667
    Prev
    Next
    INDEX
    Explanations

    table

    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
    :✨
    -0.70
    تقاوى
    -0.58
     ***!
    -0.54
    antası
    -0.53
     thermomix
    -0.50
     Gump
    -0.50
     firebaseConfig
    -0.49
    okovic
    -0.48
    boldmath
    -0.47
     earthquake
    -0.46
    POSITIVE LOGITS
    saurus
    0.55
    paces
    0.55
    oredCriteria
    0.53
    WaitGroup
    0.52
    pois
    0.52
    ьаж
    0.51
    pendente
    0.50
    corrência
    0.50
    pop
    0.48
    /**
    0.48
    Activations Density 0.007%

    No Known Activations