© 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. 1-RES-MATRYOSHKA-DC
    7. 361
    Prev
    Next
    INDEX
    Explanations

    references to specific technical and statistical details

    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
     a
    -0.68
     NSCoder
    -0.66
    SequentialGroup
    -0.61
    grana
    -0.60
    fortun
    -0.58
     the
    -0.57
    makeText
    -0.57
    CPtr
    -0.57
    ParallelGroup
    -0.56
    addWidget
    -0.55
    POSITIVE LOGITS
     Efq
    0.83
     Jefus
    0.75
     enfans
    0.74
     piú
    0.72
     Chriftian
    0.72
     moschino
    0.70
     parachoque
    0.69
     ſtate
    0.68
     Majefty
    0.68
     Shakspeare
    0.68
    Activations Density 27.193%

    No Known Activations