© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1531
    Prev
    Next
    INDEX
    Explanations

    proposals and deals

    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
     offer
    -2.16
     Offer
    -1.95
    offer
    -1.91
    Offer
    -1.90
    OFFER
    -1.51
     OFFER
    -1.46
     offering
    -1.27
    offering
    -1.24
    offers
    -1.21
     Offering
    -1.20
    POSITIVE LOGITS
     a
    0.63
     something
    0.54
    ر
    0.49
     the
    0.49
     an
    0.49
    tep
    0.49
     their
    0.48
    anco
    0.47
    uri
    0.47
     compagn
    0.46
    Activations Density 0.346%

    No Known Activations