© 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. 1-RES-MATRYOSHKA-DC
    7. 415
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific measurement data, especially related to quantified levels or concentrations

    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
     kasarigan
    -0.57
    --
    -0.56
    ]--;
    -0.53
    ceb
    -0.53
     Gers
    -0.51
    . 
    -0.51
     
    -0.50
     
    -0.50
    ------
    -0.49
      
    -0.49
    POSITIVE LOGITS
     ±
    3.81
    ±
    3.55
     +/-
    2.97
     (±
    2.67
     ± 
    2.45
    +/-
    2.31
     +-
    2.14
    pm
    2.13
    
    1.94
    ± 
    1.59
    Activations Density 0.333%

    No Known Activations