© 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. 816
    Prev
    Next
    INDEX
    Explanations

    the word "remove" and its variants.

    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
    LookAnd
    -0.58
     htons
    -0.56
    izoen
    -0.55
     vyu
    -0.54
     Porta
    -0.53
     Fittings
    -0.53
     malheur
    -0.53
    vastatin
    -0.52
    hésite
    -0.51
     fittings
    -0.51
    POSITIVE LOGITS
     Removal
    1.79
     remove
    1.78
     removal
    1.78
     Remove
    1.71
     removing
    1.69
     removes
    1.68
     REMOVE
    1.66
    remove
    1.63
     Removing
    1.63
     removed
    1.63
    Activations Density 1.049%

    No Known Activations