© 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. 5-CLT-HP
    7. 821
    Prev
    Next
    INDEX
    Explanations

    build

    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
     initComponents
    -0.59
     EconPapers
    -0.56
    GIVEREF
    -0.51
     protoimpl
    -0.51
    erializer
    -0.47
    Documented
    -0.47
    PONENTS
    -0.46
    liances
    -0.46
    djangoproject
    -0.46
    ::_('
    -0.46
    POSITIVE LOGITS
     تضيفلها
    0.68
    KEYCODE
    0.59
     ouvertes
    0.58
     Gefahr
    0.57
    rimidine
    0.56
    IntoConstraints
    0.55
    balleur
    0.53
    Locator
    0.52
     vectorielles
    0.52
     navideñas
    0.52
    Activations Density 0.000%

    No Known Activations