© 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. 3714
    Prev
    Next
    INDEX
    Explanations

    references to affordability and cost-effectiveness

    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
    ½
    -1.00
     vectorielle
    -0.80
     zubehör
    -0.79
     vnnd
    -0.77
    ChildScrollView
    -0.77
     ſever
    -0.75
     overland
    -0.75
     whoſe
    -0.75
    MLLoader
    -0.73
     feroit
    -0.73
    POSITIVE LOGITS
     half
    2.08
     Half
    1.77
    Half
    1.77
    half
    1.70
     HALF
    1.52
    HALF
    1.30
     halfway
    1.02
     halv
    1.02
     setengah
    0.98
     halves
    0.90
    Activations Density 0.012%

    No Known Activations