© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13734
    Prev
    Next
    INDEX
    Explanations

    specific gene or protein identifiers and research-related metadata

    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
    bl
    -1.51
    featureID
    -0.87
    +#+#
    -0.80
    tvguidetime
    -0.79
    niająca
    -0.75
     Biôgrafia
    -0.75
     становника
    -0.74
     насељу
    -0.73
     Seeder
    -0.69
     ostavi
    -0.68
    POSITIVE LOGITS
     BL
    1.77
    sl
    0.70
    Blan
    0.63
     Blues
    0.63
    itemBuilder
    0.59
     IMPLIED
    0.57
     Blade
    0.54
    Blues
    0.53
    WarningLevel
    0.52
     Ains
    0.52
    Activations Density 0.001%

    No Known Activations