© 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. 4048
    Prev
    Next
    INDEX
    Explanations

    references to storage capacity measurements

    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
    Ligações
    -0.84
     ویکی‌پدیای
    -0.83
    Clik
    -0.82
     Monfieur
    -0.82
     NSCoder
    -0.82
     esternos
    -0.81
    verwijspagina
    -0.80
    ImageContext
    -0.80
     Efq
    -0.80
     contextLoads
    -0.79
    POSITIVE LOGITS
    GB
    3.20
     GB
    2.84
    gb
    2.42
     gb
    2.11
    Gb
    1.61
     Gb
    1.27
    GBK
    1.02
     gigabyte
    1.02
    GBT
    0.76
    GBR
    0.75
    Activations Density 0.006%

    No Known Activations