© 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. 24-RES-MATRYOSHKA-DC
    7. 515
    Prev
    Next
    INDEX
    Explanations

    words related to ingredients and flavors, especially in the context of cuisine and fragrance, and also words relating to botany.

    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.24.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.24.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
    ніципалі
    -0.61
     initWithFrame
    -0.57
    PreferredItem
    -0.55
    IFORM
    -0.53
    rophore
    -0.52
     Réponses
    -0.52
    ."],
    -0.50
     الدولى
    -0.49
    AsUp
    -0.48
     يتيمه
    -0.48
    POSITIVE LOGITS
     Paglinawan
    0.70
     grapes
    0.66
     sunflower
    0.59
     almonds
    0.59
     grape
    0.59
     apples
    0.57
     peanuts
    0.57
     hops
    0.57
     soybeans
    0.56
     sunflowers
    0.56
    Activations Density 0.591%

    No Known Activations