© 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. 0-RES-MATRYOSHKA-DC
    7. 12617
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bl" (likely indicating the neuron is looking for the word "Bl" or similar variations)

    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
    -1.24
     autorytatywna
    -0.90
     دیکھیے
    -0.81
    adpleegd
    -0.77
     disambiguazione
    -0.75
     GetEnumerator
    -0.68
     vPvB
    -0.67
    ophageal
    -0.64
     Wiktionnaire
    -0.60
     IDisposable
    -0.60
    POSITIVE LOGITS
     Bl
    2.00
    Bl
    1.97
     bl
    1.82
     Blom
    0.85
     Blum
    0.82
    bl
    0.81
     Blu
    0.60
    Blu
    0.60
     Blumen
    0.57
     blu
    0.56
    Activations Density 0.001%

    No Known Activations