© 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. 4-CLT-HP
    7. 339
    Prev
    Next
    INDEX
    Explanations

    beds

    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
    !")
    -0.58
     JpaRepository
    -0.58
    alyptus
    -0.54
    mmc
    -0.53
     Zoro
    -0.52
     binoculars
    -0.52
     Iri
    -0.51
    таратура
    -0.50
    LocalizedString
    -0.50
     VOTE
    -0.49
    POSITIVE LOGITS
     EconPapers
    0.85
    SequentialGroup
    0.64
     rowspan
    0.57
    diğini
    0.52
    camisa
    0.50
    OGA
    0.49
    uerre
    0.49
    dags
    0.48
    lagt
    0.48
    DoubleQuotes
    0.48
    Activations Density 0.024%

    No Known Activations