© 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. 376
    Prev
    Next
    INDEX
    Explanations

    differences or variations in measurement or data

    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
     various
    -0.85
    various
    -0.83
     különböző
    -0.74
    Various
    -0.71
     Various
    -0.69
     different
    -0.66
     VARIOUS
    -0.60
     multiple
    -0.59
    色んな
    -0.58
    liesslich
    -0.57
    POSITIVE LOGITS
     difference
    4.06
     differences
    3.75
    difference
    3.75
     Difference
    3.66
     Differences
    3.59
    Difference
    3.53
    Differences
    3.42
     DIFFERENCE
    3.42
    differences
    3.33
     différence
    3.09
    Activations Density 1.156%

    No Known Activations