© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2547
    Prev
    Next
    INDEX
    Explanations

    the word "two"

    oai_token-act-pair · gemini-2.0-flash
    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
     a
    -0.73
     flere
    -0.49
     more
    -0.48
     eines
    -0.48
     einer
    -0.45
     een
    -0.45
     another
    -0.44
     unui
    -0.44
     certain
    -0.43
    ollectionView
    -0.43
    POSITIVE LOGITS
    +#+#
    0.99
     تضيفلها
    0.96
     betweenstory
    0.88
     onCancelled
    0.88
    Ambos
    0.86
     beide
    0.84
     kasarigan
    0.82
     Beide
    0.82
     beiden
    0.81
     Ambos
    0.79
    Activations Density 0.084%

    No Known Activations