© 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. 6-RES-MATRYOSHKA-DC
    7. 285
    Prev
    Next
    INDEX
    Explanations

    the word "use" or "using" following certain prepositions such as "of", "for", and "as".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppComponent
    -0.92
    ValueStyle
    -0.91
     NgModule
    -0.86
    elemField
    -0.86
    ConstraintMaker
    -0.85
     nakalista
    -0.83
    :✨
    -0.81
     autorytatywna
    -0.80
     bezeichneter
    -0.80
    WebVitals
    -0.79
    POSITIVE LOGITS
     use
    2.13
     Use
    1.95
     uses
    1.90
    Use
    1.80
     USE
    1.77
     Uses
    1.70
     usage
    1.66
    use
    1.63
     used
    1.63
    ToUse
    1.59
    Activations Density 1.665%

    No Known Activations