© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91934
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    expandindo
    -0.66
    Revenir
    -0.64
    فيه
    -0.62
    DropColumn
    -0.62
     Wikispecies
    -0.60
     становника
    -0.57
    MENAFN
    -0.56
     OMITBAD
    -0.55
    期刊论文
    -0.55
    áles
    -0.54
    POSITIVE LOGITS
    atelle
    0.48
     protoimpl
    0.46
     internetowa
    0.46
     springfox
    0.45
     modern
    0.42
     this
    0.42
    TagMode
    0.42
    working
    0.41
    modern
    0.41
    mixin
    0.41
    Activations Density 0.001%

    No Known Activations