© 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. 20-CLT-HP
    7. 76552
    Prev
    Next
    INDEX
    Explanations

    Financial costs and prices

    np_max-act-logits · 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
     وتسجيلات
    -0.93
     températures
    -0.77
    Price
    -0.75
    Демографія
    -0.72
     Price
    -0.71
     refroid
    -0.71
     Pricing
    -0.71
    PRICE
    -0.70
     PRICE
    -0.69
     espirituales
    -0.67
    POSITIVE LOGITS
     asking
    0.64
     fetch
    0.59
     fetching
    0.56
    asking
    0.55
     ask
    0.52
     spot
    0.52
     cours
    0.51
     dear
    0.51
     wholesale
    0.50
     commanded
    0.49
    Activations Density 0.002%

    No Known Activations