© 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. 94731
    Prev
    Next
    INDEX
    Explanations

    conjunctions/intensifiers

    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
     dàng
    -0.48
    fony
    -0.47
    lwjgl
    -0.45
    UAL
    -0.43
     Trilogy
    -0.42
     Archiproducts
    -0.41
    hlander
    -0.40
     （
    -0.40
    phany
    -0.40
    trine
    -0.39
    POSITIVE LOGITS
    bootstrapcdn
    0.81
    存于互联网档案馆
    0.69
     ComVisible
    0.66
     فريبيس
    0.64
    ंदीखरीदारी
    0.63
     nakalista
    0.61
     ProtoMessage
    0.60
     onResponse
    0.59
     referenties
    0.59
    +#+#
    0.59
    Activations Density 0.189%

    No Known Activations