© 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. 90640
    Prev
    Next
    INDEX
    Explanations

    Email updates

    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
     moment
    -0.73
     oeuvre
    -0.55
    Hozzáférés
    -0.54
     resonance
    -0.54
    omini
    -0.54
    UnusedPrivate
    -0.54
    ryl
    -0.53
    Viited
    -0.53
     loose
    -0.53
    sprung
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.63
    المشاركات
    0.61
     wikipagina
    0.56
     habet
    0.54
    formik
    0.54
    harapkan
    0.53
    er
    0.53
    ArrowToggle
    0.52
     TextAppearance
    0.51
     suficientemente
    0.51
    Activations Density 0.521%

    No Known Activations