© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5768
    Prev
    Next
    INDEX
    Explanations

    references to the usage or application of a particular concept or method

    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
     '',
    -0.69
     rhestr
    -0.68
    Empereur
    -0.67
    élection
    -0.67
     Geraadpleegd
    -0.66
    qrstuvwxyz
    -0.64
     Seel
    -0.63
    gründung
    -0.60
    rø
    -0.59
     considérée
    -0.59
    POSITIVE LOGITS
    Usage
    2.81
     Usage
    2.75
     usage
    2.63
    usage
    2.56
    USAGE
    2.33
     USAGE
    2.22
     usages
    1.87
    usages
    1.68
     consumption
    1.08
     utilization
    0.95
    Activations Density 0.034%

    No Known Activations