© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    references to a specific molecular marker, B

    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
    +#+#
    -0.81
     bVar
    -0.77
     للمعارف
    -0.75
     HasFactory
    -0.74
    batore
    -0.68
    complexContent
    -0.67
    expandindo
    -0.65
    b
    -0.65
    abstractmethod
    -0.64
    новниш
    -0.64
    POSITIVE LOGITS
    B
    1.67
     B
    1.59
    Ｂ
    0.86
     getB
    0.83
     Bs
    0.78
     Б
    0.75
    𝐵
    0.75
    Bs
    0.71
    Bz
    0.69
     Bani
    0.68
    Activations Density 0.196%

    No Known Activations