© 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. 0-CLT-HP
    7. 95476
    Prev
    Next
    INDEX
    Explanations

    Pap

    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
     Pari
    -0.63
    ardini
    -0.57
     Dlatego
    -0.56
    pari
    -0.52
    PAD
    -0.48
    HtmlAttribute
    -0.47
    ossa
    -0.46
    hoots
    -0.44
     odkazy
    -0.43
     Dafür
    -0.42
    POSITIVE LOGITS
    
    0.71
    UnitTesting
    0.64
    ьаж
    0.60
    Diweddarwch
    0.59
    PBS
    0.58
     متعلقه
    0.56
    REME
    0.56
    means
    0.55
     moyens
    0.55
    stylers
    0.55
    Activations Density 1.577%

    No Known Activations