© 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. 5001
    Prev
    Next
    INDEX
    Explanations

    references to repeated occurrences or repetitions

    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
     Once
    -1.40
     once
    -1.38
    Once
    -1.38
     ONCE
    -1.30
    once
    -1.27
    ONCE
    -1.20
    一旦
    -0.81
     einmal
    -0.70
     vez
    -0.66
    ]--;
    -0.66
    POSITIVE LOGITS
     again
    2.20
    again
    2.00
    Again
    1.93
     Again
    1.92
     novamente
    1.67
     AGAIN
    1.59
    AGAIN
    1.58
     igjen
    1.55
     nuevamente
    1.39
     igen
    1.35
    Activations Density 0.019%

    No Known Activations