© 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. 2-RES-MATRYOSHKA-DC
    7. 5860
    Prev
    Next
    INDEX
    Explanations

    code related to removing or deleting elements in programming

    oai_token-act-pair · gpt-4.1-nano
    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
    extAlignment
    -0.76
     itſelf
    -0.73
    rubin
    -0.70
     ویکی‌پدیای
    -0.69
    reht
    -0.66
     tslint
    -0.65
     $_"
    -0.64
    atimes
    -0.63
     Majefty
    -0.63
    Kini
    -0.63
    POSITIVE LOGITS
    remove
    1.32
    Remove
    0.75
     remove
    0.67
    complexContent
    0.67
    REMOVE
    0.66
     Remove
    0.64
    šku
    0.57
     REMOVE
    0.55
     ja
    0.55
    XXI
    0.54
    Activations Density 0.006%

    No Known Activations