© 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. 0-CLT-HP
    7. 43000
    Prev
    Next
    INDEX
    Explanations

    brands, products, technical

    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
    tus
    -0.52
     contribu
    -0.48
     Mass
    -0.45
    usu
    -0.44
     Kuhn
    -0.44
     bo
    -0.44
    InlineData
    -0.43
     com
    -0.42
     Bo
    -0.41
    ignal
    -0.41
    POSITIVE LOGITS
     élas
    0.86
     déchir
    0.81
     colorés
    0.81
     réguli
    0.79
     sentiers
    0.78
    PerformLayout
    0.77
     blessés
    0.77
     rempliss
    0.76
     normaux
    0.75
     aveug
    0.75
    Activations Density 0.088%

    No Known Activations