© 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. 18-RES-MATRYOSHKA-DC
    7. 424
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on several disparate concepts: medical information, company details specifically related to "SnackNation", probability questions, general discussions around technology, and official board meetings/announcements. It is difficult to determine a singular topic the neuron identifies

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.85
     Diſ
    -0.85
     houſe
    -0.85
     ſy
    -0.82
     Majefty
    -0.79
     AppColors
    -0.78
     Houſe
    -0.76
     ſen
    -0.74
     ſaid
    -0.73
     ſche
    -0.73
    POSITIVE LOGITS
     again
    0.69
    同上
    0.64
    </b>
    0.60
     +
    0.59
     to
    0.57
      
    0.57
     Réponses
    0.56
    ditto
    0.56
    出版年
    0.56
    oneofs
    0.56
    Activations Density 6.844%

    No Known Activations