© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8946
    Prev
    Next
    INDEX
    Explanations

    reading, read more

    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
     насељу
    -0.61
    
    -0.59
    jection
    -0.56
    /**
    -0.56
    Tembelea
    -0.56
    --){
    -0.55
     Meksiku
    -0.55
     Wicidata
    -0.55
    cepan
    -0.54
    êcher
    -0.54
    POSITIVE LOGITS
    saurus
    0.43
    ROIT
    0.43
    ArgumentParser
    0.42
    εσ
    0.40
    ROID
    0.40
    by
    0.40
    SerializedSize
    0.39
    warzys
    0.39
    Carcinogenicity
    0.38
    anskrit
    0.38
    Activations Density 0.096%

    No Known Activations