© 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. 4-CLT-HP
    7. 980
    Prev
    Next
    INDEX
    Explanations

    inventory, supply, availability

    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
     صوتيه
    -0.73
     Paglinawan
    -0.64
     pinulongan
    -0.61
     BorderSide
    -0.54
    AutoresizingMask
    -0.54
    __))
    -0.53
     Chwiliwch
    -0.52
     Energies
    -0.52
    الحياه
    -0.51
     ujednoznacz
    -0.51
    POSITIVE LOGITS
     of
    0.60
    IsContent
    0.50
    ěry
    0.50
    footnote
    0.50
    colhead
    0.50
    ConverterFactory
    0.48
    alamus
    0.47
     hieß
    0.46
    GraphQL
    0.46
    binaan
    0.45
    Activations Density 0.003%

    No Known Activations