© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 701
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    enterOuterAlt
    -0.50
    HasAnnotation
    -0.49
    createNewFile
    -0.47
    aarrggbb
    -0.47
    ärzt
    -0.47
    ])){
    -0.45
    achute
    -0.44
    RenderAtEndOf
    -0.43
    ExtendWith
    -0.41
     girl
    -0.40
    POSITIVE LOGITS
    คัญ
    0.61
     births
    0.60
     Roskov
    0.58
    الإنجليزية
    0.57
     silenzio
    0.56
     passés
    0.54
    Deals
    0.54
    sizes
    0.54
    исленность
    0.54
     Sizes
    0.53
    Activations Density 0.005%

    No Known Activations