© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3130
    Prev
    Next
    INDEX
    Explanations

    Code, dates, legal documents

    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
    ItemBackground
    -0.57
    ENEFITS
    -0.54
    sizeCache
    -0.53
    dafx
    -0.53
    <eos>
    -0.53
     ComVisible
    -0.52
     VERSITY
    -0.50
     intStringLen
    -0.49
    WireFormat
    -0.48
    PRWEB
    -0.48
    POSITIVE LOGITS
    ChildScrollView
    0.75
     MonoBehaviour
    0.71
     تانيه
    0.66
    ագրություններ
    0.64
    omiast
    0.60
    IntoConstraints
    0.60
    InstanceState
    0.60
     للمعارف
    0.60
     שוליים
    0.60
     LUMP
    0.59
    Activations Density 0.175%

    No Known Activations