© 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. 5984
    Prev
    Next
    INDEX
    Explanations

    references to specific identification codes or unique IDs within technical or data-related texts

    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
    AndroidJUnit
    -0.68
    Varint
    -0.65
    DBNull
    -0.63
    id
    -0.60
    سمبر
    -0.59
     ».
    -0.58
    setBounds
    -0.58
    )»
    -0.56
    postDelayed
    -0.55
     Aub
    -0.54
    POSITIVE LOGITS
     ID
    1.84
    ID
    1.79
     IDs
    1.23
    IDs
    1.15
     getID
    1.10
    itemID
    0.98
    userID
    0.98
    ByID
    0.94
     userID
    0.93
    getID
    0.91
    Activations Density 0.068%

    No Known Activations