© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4621
    Prev
    Next
    INDEX
    Explanations

    Changes and trends

    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
    -0.78
    oa̍t
    -0.68
    RenderAtEndOf
    -0.65
    fromnode
    -0.64
    HasForeignKey
    -0.63
    Rüyada
    -0.63
     calendriers
    -0.62
     disambiguazione
    -0.59
     ivelany
    -0.59
    hadiran
    -0.59
    POSITIVE LOGITS
     further
    0.47
     widely
    0.46
     daily
    0.46
     Alhambra
    0.45
    fillType
    0.44
     meas
    0.43
     continually
    0.43
    Verkehr
    0.43
    cupertino
    0.42
     among
    0.42
    Activations Density 0.004%

    No Known Activations