© 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. 7355
    Prev
    Next
    INDEX
    Explanations

    segments of text containing licensing or copyright information

    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
     itſelf
    -2.27
     Efq
    -2.20
     myſelf
    -2.17
     Савезне
    -2.14
    ^(@)
    -1.95
     Majefty
    -1.95
     pleaſure
    -1.93
    ſelf
    -1.92
     leaſt
    -1.92
    ſelves
    -1.91
    POSITIVE LOGITS
    .
    1.28
    1
    1.27
     
    1.26
    2
    1.20
    ,
    1.13
    (
    1.10
     (
    1.09
    4
    1.09
    ↵
    1.09
    0
    1.07
    Activations Density 1.322%

    No Known Activations