© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    references to selection pressures and their variation over time and space

    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
     decide
    -0.85
     Decide
    -0.82
    decide
    -0.78
     decided
    -0.75
     Decided
    -0.73
     decid
    -0.72
    decided
    -0.72
    Decide
    -0.71
     chose
    -0.71
     Choose
    -0.69
    POSITIVE LOGITS
     selection
    2.64
     Selection
    2.56
    Selection
    2.44
    selection
    2.44
     SELECTION
    2.25
    SELECTION
    2.05
     selections
    1.87
     Selections
    1.86
    Selections
    1.69
    selections
    1.65
    Activations Density 0.019%

    No Known Activations