© 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. 621
    Prev
    Next
    INDEX
    Explanations

    citing information

    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
     Efq
    -1.08
     ExecuteAsync
    -1.06
    parsedMessage
    -1.05
     fieldNum
    -0.93
    MessageTagHelper
    -0.91
    complexType
    -0.90
     CWE
    -0.89
     resourceCulture
    -0.88
     itſelf
    -0.88
     otomatig
    -0.86
    POSITIVE LOGITS
     "
    0.46
     '
    0.44
    <eos>
    0.41
    ?
    0.40
     ("
    0.40
    ("
    0.39
    ('
    0.39
    </b>
    0.38
     “
    0.37
     ''
    0.37
    Activations Density 0.006%

    No Known Activations