© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73653
    Prev
    Next
    INDEX
    Explanations

    Addresses and citations

    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
    KommentareTeilen
    -0.72
    TypedDataSet
    -0.61
    adaptiveStyles
    -0.56
    Datuak
    -0.56
     hant
    -0.53
    itemBuilder
    -0.53
     jScrollPane
    -0.53
     Italijanski
    -0.51
     Turi
    -0.50
    FDRE
    -0.50
    POSITIVE LOGITS
    เดียว
    0.49
    Diweddarwch
    0.49
     gjø
    0.49
     succede
    0.47
     singoli
    0.47
    goes
    0.47
    ıştı
    0.46
     goes
    0.44
    ress
    0.44
    Grand
    0.43
    Activations Density 0.000%

    No Known Activations