© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    code

    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
    RegressionTest
    -0.66
     يتيمه
    -0.65
    ConstraintMaker
    -0.64
    FontOfSize
    -0.63
     initComponents
    -0.62
    Hozzáférés
    -0.61
    .*")]
    -0.60
    delwed
    -0.60
     насељу
    -0.60
    Vidite
    -0.60
    POSITIVE LOGITS
    []>
    0.48
    <%=
    0.47
    ligan
    0.43
    mored
    0.41
    nameof
    0.41
    asantry
    0.40
    χή
    0.40
    gmd
    0.40
     transferir
    0.40
    нъ
    0.39
    Activations Density 0.009%

    No Known Activations