© 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. 0-RES-MATRYOSHKA-DC
    7. 14881
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or term, often repeated with slight variations

    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
    IVEREF
    -0.72
     artistique
    -0.61
    moveToFirst
    -0.57
     Waray
    -0.57
    XtraEditors
    -0.56
    findOrFail
    -0.56
    setEditable
    -0.55
     trúc
    -0.55
     inden
    -0.54
    serviceWorker
    -0.53
    POSITIVE LOGITS
    pel
    3.42
     pel
    3.28
     Pel
    3.05
    Pel
    2.98
    PEL
    2.11
     PEL
    1.92
     pelt
    1.25
    pela
    1.13
    pell
    1.07
    pelo
    1.05
    Activations Density 0.001%

    No Known Activations