© 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. 97318
    Prev
    Next
    INDEX
    Explanations

    Code examples

    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
     it
    -0.67
     they
    -0.56
     the
    -0.56
     this
    -0.52
     expands
    -0.52
     creates
    -0.52
     newly
    -0.51
     finer
    -0.50
    hates
    -0.49
    inex
    -0.48
    POSITIVE LOGITS
    UserScript
    0.80
     שוליים
    0.65
    Kaynakça
    0.59
    Referencias
    0.58
     становника
    0.57
    paravant
    0.57
    harusnya
    0.55
     sẻ
    0.54
    ">—
    0.53
     förr
    0.50
    Activations Density 0.013%

    No Known Activations