© 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. 5-CLT-HP
    7. 4058
    Prev
    Next
    INDEX
    Explanations

    addresses, numbers, legal matters

    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
    はじめに
    -0.65
     terecht
    -0.57
     EconPapers
    -0.52
    ग्री
    -0.51
     actif
    -0.50
     igenom
    -0.50
     سكانية
    -0.49
     voordeel
    -0.49
     siitä
    -0.49
     abstrait
    -0.49
    POSITIVE LOGITS
    parsedMessage
    0.60
     فريبيس
    0.55
     nargin
    0.54
     invites
    0.51
    PhysRev
    0.50
    amsmath
    0.50
    ?,?,
    0.50
    EndContext
    0.49
    basicConfig
    0.48
    ErrUnexpectedEOF
    0.46
    Activations Density 0.000%

    No Known Activations