© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19729
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Daß
    -0.66
     bouche
    -0.60
     årets
    -0.57
     vallée
    -0.55
    knię
    -0.52
     nameof
    -0.50
    پرو
    -0.50
    mē
    -0.49
    /><
    -0.49
     banho
    -0.49
    POSITIVE LOGITS
    bootstrapcdn
    0.90
    Autoritní
    0.75
    لينكات
    0.73
    GEBURTSDATUM
    0.70
    ScopeManager
    0.69
     خارجية
    0.68
     استنادى
    0.68
    IUrlHelper
    0.65
     مُعرِّف
    0.64
    posedge
    0.62
    Activations Density 0.001%

    No Known Activations