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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5690
    Prev
    Next
    INDEX
    Explanations

    terms related to restoration or recovery processes

    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
    labus
    -0.70
     financières
    -0.66
    goku
    -0.64
    paccio
    -0.64
    سرائيلي
    -0.63
    ʒ
    -0.63
     McDaniel
    -0.62
    Kni
    -0.62
    TAGE
    -0.61
     arrière
    -0.60
    POSITIVE LOGITS
     Restore
    1.43
     restore
    1.38
    restore
    1.31
     restores
    1.30
     Restoration
    1.30
     restored
    1.24
     restoration
    1.23
     restorations
    1.20
    Restoration
    1.18
    Restore
    1.16
    Activations Density 0.017%

    No Known Activations