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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2534
    Prev
    Next
    INDEX
    Explanations

    random excerpts, general text

    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
    principalTable
    -0.63
    ronique
    -0.58
    ismet
    -0.58
    featureID
    -0.58
    EndProject
    -0.56
    SharedDtor
    -0.56
     prez
    -0.54
     województwie
    -0.53
    findpost
    -0.50
    حياته
    -0.50
    POSITIVE LOGITS
    väg
    0.55
     remercier
    0.51
    UnsafeEnabled
    0.51
     skola
    0.51
    uality
    0.50
    urlpatterns
    0.48
    ulaski
    0.48
     réaliste
    0.48
     csalá
    0.47
    urge
    0.47
    Activations Density 0.001%

    No Known Activations