© 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. 5-CLT-HP
    7. 91020
    Prev
    Next
    INDEX
    Explanations

    find

    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
    Negative Logits
    tvguidetime
    -0.76
    
    -0.68
     defStyle
    -0.57
    مصادر
    -0.54
    ########.
    -0.50
    onViewCreated
    -0.49
    reditation
    -0.49
    styleType
    -0.48
    opsida
    -0.47
     ***!
    -0.46
    POSITIVE LOGITS
    انجليز
    0.63
     Reſ
    0.56
     Diſ
    0.55
    phens
    0.54
     grito
    0.54
    rolid
    0.53
    aties
    0.52
    sendRedirect
    0.52
    সং
    0.52
     Lambeth
    0.52
    Activations Density 0.043%

    No Known Activations