© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    patterns involving hexadecimal or digital codes

    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
     ENTER
    -0.85
     enter
    -0.84
    Enter
    -0.80
     Enter
    -0.77
     enters
    -0.76
     entered
    -0.76
    Into
    -0.69
    ENTER
    -0.66
    enter
    -0.66
     Into
    -0.65
    POSITIVE LOGITS
    Entry
    2.14
    entry
    2.03
     Entry
    1.98
     entry
    1.80
    ENTRY
    1.78
     ENTRY
    1.69
     Entries
    1.41
     entries
    1.41
    entries
    1.41
    Entries
    1.41
    Activations Density 0.013%

    No Known Activations