© 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. 4-CLT-HP
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    Cooking measurements

    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
    Reklama
    -0.54
    seteq
    -0.53
    Altri
    -0.53
    Gweler
    -0.51
    ystems
    -0.50
    syms
    -0.48
    ▼
    -0.48
    atschappij
    -0.47
    medik
    -0.47
    ethene
    -0.47
    POSITIVE LOGITS
    ful
    0.85
    fuls
    0.83
     CreateTagHelper
    0.75
    FUL
    0.66
    Geplaatst
    0.65
    AccessorTable
    0.64
    full
    0.63
    исленность
    0.62
    KommentareTeilen
    0.59
    Scoop
    0.58
    Activations Density 0.019%

    No Known Activations