© 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. 92077
    Prev
    Next
    INDEX
    Explanations

    Groups of people

    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
    存于互联网档案馆
    -1.03
    Personensuche
    -0.88
     betweenstory
    -0.87
     MainAxisSize
    -0.77
    makeConstraints
    -0.75
    ActionCreators
    -0.73
    Portály
    -0.73
    ^(@)
    -0.72
    chọn
    -0.72
    cách
    -0.71
    POSITIVE LOGITS
    ':
    0.46
     sä
    0.42
     saving
    0.39
    ":
    0.37
    ãs
    0.36
     colabor
    0.35
    .:
    0.35
    ukone
    0.35
     ten
    0.35
    '.
    0.35
    Activations Density 0.002%

    No Known Activations