© 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. 0-CLT-HP
    7. 38629
    Prev
    Next
    INDEX
    Explanations

    record

    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
     recording
    -0.57
     dentaire
    -0.57
     recordings
    -0.50
     Recordings
    -0.47
    tvguidetime
    -0.46
    Recording
    -0.45
     alltså
    -0.45
    IUrlHelper
    -0.44
    thâu
    -0.44
     ferons
    -0.44
    POSITIVE LOGITS
     становника
    0.73
    BeginContext
    0.68
     disqual
    0.67
     Phari
    0.63
     autorytatywna
    0.62
     consecration
    0.61
    olerance
    0.60
    orestation
    0.59
     Romans
    0.59
     Philist
    0.58
    Activations Density 0.101%

    No Known Activations