© 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. 20-CLT-HP
    7. 71573
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
    CategoryId
    -0.43
    relli
    -0.41
     termica
    -0.40
     khuôn
    -0.39
    IONES
    -0.38
     terceira
    -0.38
     vapeur
    -0.38
     étages
    -0.38
     endfor
    -0.36
     Evalu
    -0.36
    POSITIVE LOGITS
    TagMode
    0.86
     utafitiHapana
    0.81
    +#+#
    0.79
     NSCoder
    0.79
    complexContent
    0.78
     كومونز
    0.76
    
    0.75
     ModelExpression
    0.75
     AssemblyCulture
    0.74
     betweenstory
    0.71
    Activations Density 0.001%

    No Known Activations