© 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. 1-CLT-HP
    7. 10629
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     propOrder
    -1.05
    featureID
    -1.04
    parsedMessage
    -0.98
    Personensuche
    -0.94
    ViewFeatures
    -0.92
     Мексичка
    -0.92
    ValueStyle
    -0.91
    NameInMap
    -0.91
     Monfieur
    -0.91
    TestingModule
    -0.89
    POSITIVE LOGITS
    m
    0.58
    k
    0.55
    n
    0.50
    0
    0.50
    x
    0.49
    d
    0.48
    μ
    0.47
    =
    0.45
    h
    0.45
    g
    0.45
    Activations Density 0.009%

    No Known Activations