© 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. 502
    Prev
    Next
    INDEX
    Explanations

    comfort and luxury

    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
    usermodel
    -0.47
     hefyd
    -0.46
     pouvoirs
    -0.45
    жению
    -0.45
    Ant
    -0.43
    Unt
    -0.42
    thorpe
    -0.42
    kaza
    -0.42
    пол
    -0.40
    といけない
    -0.40
    POSITIVE LOGITS
     OnInit
    0.68
    mybatisplus
    0.65
     much
    0.65
    awtextra
    0.65
    CrossRef
    0.62
    resizingMask
    0.61
    drawSprites
    0.60
    ătă
    0.60
    setVerticalGroup
    0.59
     متعلقه
    0.59
    Activations Density 0.003%

    No Known Activations