© 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. 5-CLT-HP
    7. 3214
    Prev
    Next
    INDEX
    Explanations

    Past descriptions and history

    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
    NOPQRST
    -0.58
    WriteBarrier
    -0.53
    viewDidLoad
    -0.53
    VersionUID
    -0.53
    BeanUtils
    -0.52
    IGraphics
    -0.52
     balanceOf
    -0.50
    alanta
    -0.49
    etCode
    -0.49
    getLatitude
    -0.49
    POSITIVE LOGITS
     ſever
    0.62
     faſt
    0.61
     fubject
    0.57
     houſe
    0.56
     ſche
    0.56
     Reſ
    0.55
     ſtre
    0.54
     Monfieur
    0.54
     defire
    0.54
     perfons
    0.54
    Activations Density 0.002%

    No Known Activations