© 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. 0-RES-MATRYOSHKA-DC
    7. 14252
    Prev
    Next
    INDEX
    Explanations

    patterns of structured textual data, such as labeled codes, numerical sequences, or formatted references

    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
     [@
    -0.96
    @
    -0.96
     @
    -0.86
    '@
    -0.81
    @_
    -0.77
    #@
    -0.76
     EconPapers
    -0.75
    ...@
    -0.73
    ,@
    -0.73
    (@
    -0.72
    POSITIVE LOGITS
    ThemeOverlay
    0.57
     سكانية
    0.53
    glPushMatrix
    0.50
    matum
    0.50
     Gründen
    0.49
    DialogContent
    0.49
     Heist
    0.49
    showroom
    0.49
     martyrdom
    0.48
    eterangan
    0.48
    Activations Density 0.266%

    No Known Activations