© 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. 0-CLT-HP
    7. 92683
    Prev
    Next
    INDEX
    Explanations

    health and risk

    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
     flowing
    -0.73
     finalised
    -0.57
     front
    -0.56
    risk
    -0.56
     emanating
    -0.54
     fell
    -0.53
     picked
    -0.53
     flowed
    -0.53
    rak
    -0.52
     cleared
    -0.51
    POSITIVE LOGITS
    ParallelGroup
    0.68
     lenker
    0.66
    +#+
    0.65
    apimachinery
    0.65
     utafitiHapana
    0.64
    外部リンク
    0.62
    titleMargin
    0.62
     وتسجيلات
    0.59
    FunctionFlags
    0.58
    mobileqq
    0.58
    Activations Density 0.095%

    No Known Activations