© 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. 20-CLT-HP
    7. 74896
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · 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
    windowFixed
    -0.46
    <?
    -0.41
    次第
    -0.36
     Corbu
    -0.36
     present
    -0.36
    Datuak
    -0.36
    remes
    -0.36
    ét
    -0.36
    <thead>
    -0.35
     waren
    -0.34
    POSITIVE LOGITS
     happen
    1.42
    happen
    1.28
     Happen
    1.22
     occur
    1.09
     happens
    0.99
    happens
    0.98
    occur
    0.97
     Happens
    0.96
    happened
    0.93
     happened
    0.93
    Activations Density 0.000%

    No Known Activations