© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4332
    Prev
    Next
    INDEX
    Explanations

    inventions and methods

    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
     referenties
    -1.04
     HasFactory
    -0.71
    󠁿
    -0.70
     >=",
    -0.69
    rawdź
    -0.67
    DeleteBehavior
    -0.65
     cherchés
    -0.65
     gabbana
    -0.65
    Kariera
    -0.65
    yarnpkg
    -0.64
    POSITIVE LOGITS
     me
    0.43
     akong
    0.41
    metic
    0.39
     initComponents
    0.39
     architectures
    0.38
    WindowManager
    0.36
    configurable
    0.35
    بوابة
    0.34
     systému
    0.34
    ónde
    0.34
    Activations Density 0.071%

    No Known Activations