© 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. 94027
    Prev
    Next
    INDEX
    Explanations

    for

    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
    vece
    -0.57
    TabIndex
    -0.54
     ag
    -0.51
    WireFormat
    -0.49
    RTEX
    -0.48
    StructEnd
    -0.48
    OK
    -0.47
     máximo
    -0.45
     giovan
    -0.44
     traditionnels
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.66
    Tembelea
    0.62
    ardia
    0.61
     اكتوبر
    0.60
    الحياه
    0.59
    __);
    0.59
     صوتيه
    0.58
     الدولى
    0.56
    OGND
    0.54
    ViewFeatures
    0.54
    Activations Density 0.019%

    No Known Activations