© 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. 92238
    Prev
    Next
    INDEX
    Explanations

    transistors

    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
     الحره
    -0.54
    collants
    -0.52
    farwyddwr
    -0.52
     للمعارف
    -0.49
    يميديا
    -0.49
     Genre
    -0.49
     Moi
    -0.46
     guardians
    -0.46
     vincere
    -0.46
     Minerals
    -0.46
    POSITIVE LOGITS
    abestanden
    0.65
    
    0.54
    úrate
    0.52
    aphne
    0.51
    EndInit
    0.49
     estekak
    0.48
     patty
    0.48
    AddTagHelper
    0.47
    tawesome
    0.47
    ylvania
    0.47
    Activations Density 0.010%

    No Known Activations