Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14373
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, such as notable persons or historical figures

    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
    2
    -0.85
    1
    -0.82
    0
    -0.77
    3
    -0.60
    7
    -0.60
    5
    -0.60
    4
    -0.59
    9
    -0.54
    8
    -0.53
    6
    -0.50
    POSITIVE LOGITS
     autorytatywna
    1.35
     nakalista
    1.14
    SourceChecksum
    1.10
    RegressionTest
    1.05
    новништво
    0.96
    Rüyada
    0.96
    rungsseite
    0.88
    Manbalar
    0.86
     &___
    0.85
    :✨
    0.84
    Activations Density 0.452%

    No Known Activations