© 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. 42852
    Prev
    Next
    INDEX
    Explanations

    provides/offers

    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
     offers
    -1.27
     Offers
    -1.08
     provides
    -1.06
    Offers
    -1.01
    offers
    -0.99
     Provides
    -0.95
     bietet
    -0.83
     oferece
    -0.83
     ofrece
    -0.83
     gives
    -0.82
    POSITIVE LOGITS
     Efq
    1.18
     cauſe
    1.10
     Diſ
    1.09
     itſelf
    1.05
     chofe
    1.01
     Houſe
    0.99
     faſt
    0.99
     Monfieur
    0.98
     caufe
    0.97
     Reſ
    0.97
    Activations Density 0.074%

    No Known Activations