© 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. 22-RES-MATRYOSHKA-DC
    7. 2260
    Prev
    Next
    INDEX
    Explanations

    mentions of ecdysone, a hormone involved in insect metamorphosis

    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.22.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.22.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
     Lea
    -0.47
    unus
    -0.47
    garan
    -0.46
    postDelayed
    -0.46
     Lam
    -0.45
    ylate
    -0.45
    itores
    -0.45
    ULE
    -0.44
     sea
    -0.43
     traz
    -0.43
    POSITIVE LOGITS
    EDEFAULT
    0.71
     مشين
    0.68
    出版年
    0.66
    Kaynakça
    0.66
     pregn
    0.65
    expandindo
    0.64
     CreateTagHelper
    0.64
    MigrationBuilder
    0.62
     betweenstory
    0.61
     resourceCulture
    0.60
    Activations Density 0.046%

    No Known Activations