© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    instructions or commands related to user input

    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
     entry
    -1.56
    Entry
    -1.46
    entry
    -1.43
     Entry
    -1.41
     ENTRY
    -1.24
    ENTRY
    -1.14
     entries
    -1.13
    Entries
    -0.97
     Entries
    -0.93
    entries
    -0.89
    POSITIVE LOGITS
    Enter
    2.14
    enter
    2.05
     Enter
    1.99
    ENTER
    1.76
     ENTER
    1.70
     enter
    1.66
    enters
    1.05
     entero
    1.04
    nEnter
    1.02
    enteric
    0.93
    Activations Density 0.022%

    No Known Activations