© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43243
    Prev
    Next
    INDEX
    Explanations

    Smoke, fake news, fried

    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
     Smoke
    -1.00
     fumée
    -0.89
    rungsseite
    -0.88
     étoient
    -0.88
     chré
    -0.88
     ainfi
    -0.86
     démocr
    -0.84
     feroit
    -0.84
    Smoke
    -0.83
     ujednoznacz
    -0.83
    POSITIVE LOGITS
     las
    0.64
    <bos>
    0.60
    ciatore
    0.51
     up
    0.50
     el
    0.50
     analysis
    0.49
    ándor
    0.49
    ItemBackground
    0.48
    VersionUID
    0.48
    erden
    0.48
    Activations Density 0.057%

    No Known Activations