© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 226
    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
     debole
    -0.62
     concernés
    -0.60
     superiori
    -0.60
     virtuales
    -0.59
     étro
    -0.59
     marquées
    -0.59
     espirituales
    -0.59
     negozi
    -0.59
    ậc
    -0.57
     legais
    -0.57
    POSITIVE LOGITS
    דש
    0.57
     accidents
    0.56
     famili
    0.55
     suicide
    0.55
     Return
    0.53
     return
    0.52
     failures
    0.51
    ombes
    0.51
     Failures
    0.51
     failure
    0.50
    Activations Density 0.002%

    No Known Activations