© 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. 6-RES-MATRYOSHKA-DC
    7. 644
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or sets of numbers with ellipses

    oai_token-act-pair · gemini-2.0-flash
    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
     nakalista
    -0.76
    SequentialGroup
    -0.73
    出版年
    -0.69
     estekak
    -0.66
    ContentAlignment
    -0.66
     ospiti
    -0.64
     suivie
    -0.63
    MLLoader
    -0.63
    ………………
    -0.63
    .........
    -0.62
    POSITIVE LOGITS
    elashes
    0.66
    LLocation
    0.64
    dots
    0.64
    зулта
    0.63
    adomo
    0.60
     AssemblyCulture
    0.59
    naments
    0.58
     Bache
    0.58
     endforeach
    0.57
     Brem
    0.57
    Activations Density 0.051%

    No Known Activations