© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7369
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to event listeners and user interface components

    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
     Majefty
    -0.76
     Efq
    -0.75
     itſelf
    -0.73
     preſent
    -0.69
     themſelves
    -0.68
    droje
    -0.67
     Monfieur
    -0.66
     occaf
    -0.65
     Perſ
    -0.63
     Diſ
    -0.63
    POSITIVE LOGITS
    dt
    3.16
     dt
    2.55
    DT
    2.50
     DT
    2.25
    Dt
    1.66
     Dt
    1.52
    dts
    1.23
    dT
    1.06
    ldt
    0.89
    dtm
    0.88
    Activations Density 0.007%

    No Known Activations