© 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. 20-CLT-HP
    7. 71781
    Prev
    Next
    INDEX
    Explanations

    Devices

    np_max-act-logits · 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
    Hentet
    -0.70
     Wicidata
    -0.65
    InjectAttribute
    -0.63
    setVerticalGroup
    -0.61
    ScopeManager
    -0.60
     EClass
    -0.58
    ArgumentParser
    -0.57
    Abp
    -0.56
    Gön
    -0.55
     Firing
    -0.54
    POSITIVE LOGITS
     devices
    0.69
     Devices
    0.63
    devices
    0.59
     elements
    0.58
    Devices
    0.54
    Elements
    0.54
     terms
    0.53
    DEVICES
    0.53
    ChildScrollView
    0.53
     Elements
    0.50
    Activations Density 0.000%

    No Known Activations