© 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. 96653
    Prev
    Next
    INDEX
    Explanations

    makeReason: Texts are often using "make" in the context of enabling or creating things.make

    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
     bezeichneter
    -0.76
    TProtocol
    -0.66
     isComment
    -0.66
    <?
    -0.63
    IntoConstraints
    -0.62
    Autoritní
    -0.61
    ValueStyle
    -0.60
     myſelf
    -0.60
     بيها
    -0.60
    stdc
    -0.59
    POSITIVE LOGITS
     a
    0.65
     significant
    0.61
     big
    0.59
     major
    0.54
     difference
    0.51
     dramatic
    0.48
     real
    0.47
     BIG
    0.47
     or
    0.47
    big
    0.47
    Activations Density 0.001%

    No Known Activations