© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4758
    Prev
    Next
    INDEX
    Explanations

    measurements of an upper bound on efficiency or success probability

    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
     lower
    -1.45
     Lower
    -1.41
    Lower
    -1.39
     LOWER
    -1.21
    lower
    -1.19
    LOWER
    -0.96
     lowering
    -0.92
     lowers
    -0.89
     lowered
    -0.75
    lowers
    -0.68
    POSITIVE LOGITS
     Low
    1.01
     low
    0.94
    Low
    0.90
    mybatisplus
    0.73
    .*")]
    0.72
    low
    0.71
     LOW
    0.70
    gatsby
    0.68
     macrop
    0.65
     dorsal
    0.63
    Activations Density 0.041%

    No Known Activations