© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1674
    Prev
    Next
    INDEX
    Explanations

    from/using

    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
    expandindo
    -0.55
     AssemblyTitle
    -0.51
     ujednoznacz
    -0.45
    contentLoaded
    -0.44
     Normdatei
    -0.43
    رشف
    -0.43
     utafitiHapana
    -0.42
     intptr
    -0.41
    .'</
    -0.41
    IRUS
    -0.41
    POSITIVE LOGITS
    glGen
    0.57
     DataTypes
    0.56
     TextInputType
    0.55
    CREAT
    0.54
    wohl
    0.52
     BoxDecoration
    0.52
    makeConstraints
    0.51
    arest
    0.50
     historiques
    0.50
    urium
    0.50
    Activations Density 0.042%

    No Known Activations