© 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. 91389
    Prev
    Next
    INDEX
    Explanations

    related

    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
    
    -0.70
    FailureListener
    -0.68
     referenties
    -0.61
    IntoConstraints
    -0.59
    ValueStyle
    -0.58
     croissants
    -0.56
     triangles
    -0.56
    ArgumentParser
    -0.55
    OCCURRED
    -0.55
     nouns
    -0.55
    POSITIVE LOGITS
     Federal
    0.51
    Federal
    0.51
    culable
    0.49
     Мексичка
    0.47
    ardan
    0.47
     Programme
    0.46
     Section
    0.46
     Relief
    0.45
    law
    0.45
     Resource
    0.45
    Activations Density 0.001%

    No Known Activations