© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 2038
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Composable
    -0.67
    UserScript
    -0.60
    ViewChild
    -0.59
     UIFont
    -0.59
    TagHelpers
    -0.57
    ValueStyle
    -0.55
    SuppressLint
    -0.54
    AndEndTag
    -0.54
     ProtoMessage
    -0.54
    knex
    -0.53
    POSITIVE LOGITS
    θεν
    0.57
    ثيق
    0.56
    -------------</
    0.51
     estekak
    0.51
    után
    0.50
     obicei
    0.49
     Vikipedi
    0.48
    nesses
    0.48
    исленность
    0.48
    kloped
    0.48
    Activations Density 0.832%

    No Known Activations