© 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. 1-CLT-HP
    7. 15569
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    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
    حياته
    -0.75
    مصادر
    -0.72
    GEBURTSDATUM
    -0.69
    发表于
    -0.59
    Спасылкі
    -0.59
    حياتها
    -0.57
    ագրություններ
    -0.57
    awtextra
    -0.55
    dafx
    -0.55
    Aiheesta
    -0.55
    POSITIVE LOGITS
    vyšší
    0.50
     dimentic
    0.48
     varandra
    0.48
     piele
    0.46
    beria
    0.45
     culoare
    0.44
     zurückge
    0.43
    phur
    0.42
     kiv
    0.42
     <<=
    0.42
    Activations Density 0.004%

    No Known Activations