© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97190
    Prev
    Next
    INDEX
    Explanations

    las

    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
    last
    -1.39
    las
    -1.33
     las
    -1.30
    LAST
    -1.29
     last
    -1.26
    lasts
    -1.23
     LAST
    -1.04
     Last
    -1.02
     lasts
    -0.95
    Last
    -0.94
    POSITIVE LOGITS
    saraba
    0.53
     muualla
    0.50
     utafitiHapana
    0.50
    mobileqq
    0.48
    mare
    0.48
     OMITBAD
    0.48
    mybatisplus
    0.47
     voluto
    0.47
    o
    0.47
     avesse
    0.47
    Activations Density 0.190%

    No Known Activations