© 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. 5-CLT-HP
    7. 98297
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ImageContext
    -0.76
    rmtree
    -0.74
    fromnode
    -0.59
    ContentValues
    -0.58
    HasForeignKey
    -0.58
    pierw
    -0.56
    pausal
    -0.55
    nosa
    -0.55
    czegó
    -0.54
     artikkelen
    -0.54
    POSITIVE LOGITS
    apimachinery
    0.52
    addContainerGap
    0.48
    yntaxException
    0.45
     المعيارى
    0.45
    -------------</
    0.43
     secundarios
    0.42
    ậc
    0.41
    newcommand
    0.40
     diret
    0.40
    存于互联网档案馆
    0.40
    Activations Density 0.003%

    No Known Activations