© 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. 5-CLT-HP
    7. 4797
    Prev
    Next
    INDEX
    Explanations

    science

    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
     astore
    -0.47
     '>=
    -0.38
    Clik
    -0.37
    raje
    -0.37
     aspects
    -0.35
    "@
    -0.34
     maging
    -0.33
     Eigen
    -0.33
     Приступљено
    -0.33
    まぁ
    -0.33
    POSITIVE LOGITS
     שוליים
    0.80
    afficheront
    0.71
     createSlice
    0.69
    enciaga
    0.66
     חיצוניים
    0.64
    Radians
    0.62
    SharedDtor
    0.62
    cipline
    0.62
    FromArgb
    0.61
    anyeol
    0.61
    Activations Density 0.001%

    No Known Activations