© 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. 1655
    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
    marginVertical
    -0.57
     [*]
    -0.55
    kazy
    -0.54
    peño
    -0.54
    ANZE
    -0.54
     gravedad
    -0.53
    ChildScrollView
    -0.52
     lccn
    -0.52
    marginHorizontal
    -0.51
    knię
    -0.50
    POSITIVE LOGITS
    afficheront
    0.73
     الرياضيه
    0.61
    LEncoder
    0.56
    Портал
    0.52
    Trayectoria
    0.52
    zuführen
    0.50
    లాలు
    0.49
     Efq
    0.48
    مراجع
    0.48
     Frie
    0.48
    Activations Density 1.707%

    No Known Activations