© 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. 1-CLT-HP
    7. 13265
    Prev
    Next
    INDEX
    Explanations

    lack of something

    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
    less
    -1.09
    LESS
    -0.90
    lessness
    -0.82
    lessly
    -0.75
     less
    -0.66
    Less
    -0.66
     Less
    -0.56
    !*\
    -0.52
     LESS
    -0.52
    OptionsMenu
    -0.52
    POSITIVE LOGITS
    Discografia
    0.64
    >';
    0.54
    Recording
    0.52
     Albe
    0.52
    abase
    0.52
    databind
    0.51
    tearDown
    0.50
    ceus
    0.49
     anum
    0.49
    égorie
    0.48
    Activations Density 0.035%

    No Known Activations