© 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. 4141
    Prev
    Next
    INDEX
    Explanations

    code/technical text

    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
     للمعارف
    -0.58
    ="@+
    -0.57
    DebuggerNonUser
    -0.50
     للاسماء
    -0.49
    iric
    -0.48
    jupiter
    -0.48
    marty
    -0.47
     lenker
    -0.47
    TemporalType
    -0.47
     بيها
    -0.47
    POSITIVE LOGITS
    izielle
    0.50
    ✨:
    0.50
    basicConfig
    0.50
    놨
    0.50
     double
    0.50
    BagConstraints
    0.49
    ündigt
    0.49
     Efq
    0.49
    caux
    0.48
    MemoryWarning
    0.48
    Activations Density 0.000%

    No Known Activations