© 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. 0-CLT-HP
    7. 45410
    Prev
    Next
    INDEX
    Explanations

    user engagement

    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
    erdings
    -0.73
    ergies
    -0.70
    urezza
    -0.63
    ClientRect
    -0.63
     ―――――
    -0.59
    fır
    -0.59
     userSchema
    -0.59
     pleaſure
    -0.59
    itespace
    -0.58
     photolibrary
    -0.58
    POSITIVE LOGITS
    ագրություններ
    0.67
    ↵↵
    0.60
     …
    0.57
    <eos>
    0.55
    ngdoc
    0.55
     .
    0.54
    …
    0.54
    存于互联网档案馆
    0.53
    Datuak
    0.52
     للاسماء
    0.51
    Activations Density 0.214%

    No Known Activations