© 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. 0-CLT-HP
    7. 97454
    Prev
    Next
    INDEX
    Explanations

    location/direction

    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
     AssemblyProduct
    -0.80
    MergeFrom
    -0.71
    SharedDtor
    -0.70
    DeleteCommand
    -0.68
    setVerticalGroup
    -0.66
    Бахар
    -0.66
    ValueGeneration
    -0.65
    encodeWith
    -0.64
    SourceChecksum
    -0.64
    SharedCtor
    -0.64
    POSITIVE LOGITS
    ENARIO
    0.45
    isinstance
    0.45
    VELAND
    0.43
    pandemic
    0.43
     intrinsically
    0.42
    #
    0.42
    hermosa
    0.42
    versity
    0.41
     sympathy
    0.41
    abancı
    0.41
    Activations Density 0.153%

    No Known Activations