© 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. 5797
    Prev
    Next
    INDEX
    Explanations

    Linq

    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
     Baillargeon
    -0.52
    ModelSerializer
    -0.51
    }{*}{
    -0.50
     RoutedEventArgs
    -0.49
    ScopeManager
    -0.48
    ofo
    -0.48
     مشين
    -0.47
     برانيه
    -0.47
    AudioSource
    -0.47
    SequentialGroup
    -0.47
    POSITIVE LOGITS
    الحياه
    0.65
    enderror
    0.64
     Galbraith
    0.54
    limus
    0.53
    millimeters
    0.53
    createNewFile
    0.52
     caviar
    0.52
    sprüng
    0.51
    AVL
    0.51
     goldfish
    0.50
    Activations Density 0.000%

    No Known Activations