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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 893
    Prev
    Next
    INDEX
    Explanations

    Military technology

    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
    webElement
    -0.51
    latimes
    -0.48
    perity
    -0.47
    ESSIONAL
    -0.44
    äfts
    -0.44
     vacas
    -0.43
    ENTY
    -0.43
    QMetaType
    -0.43
     détermination
    -0.43
    cive
    -0.42
    POSITIVE LOGITS
     ComVisible
    0.68
    GOTREF
    0.65
    ագրություններ
    0.65
     betweenstory
    0.65
     الدولى
    0.64
    Viited
    0.61
    WaitGroup
    0.60
    +#+
    0.55
    BeginContext
    0.54
    ViewFeatures
    0.52
    Activations Density 0.002%

    No Known Activations