© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15897
    Prev
    Next
    INDEX
    Explanations

    mentions of full or complete datasets, reports, or information

    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
    daq
    -0.53
     Tenden
    -0.52
     entire
    -0.52
    onia
    -0.51
     Somewhere
    -0.51
    pyplot
    -0.49
     Или
    -0.48
     præ
    -0.48
    ternal
    -0.47
     whole
    -0.47
    POSITIVE LOGITS
     Full
    1.89
    Full
    1.61
    FULL
    0.99
     Fuller
    0.98
     ProtoMessage
    0.96
     continúas
    0.92
    Fuller
    0.85
     Fullerton
    0.85
     nahilalakip
    0.82
    Fullscreen
    0.80
    Activations Density 0.004%

    No Known Activations