© 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. 16419
    Prev
    Next
    INDEX
    Explanations

    references to subsequent sections in a document

    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
     later
    -0.58
     majd
    -0.50
     originally
    -0.46
     original
    -0.46
     senere
    -0.45
    origine
    -0.44
     earlier
    -0.44
     póź
    -0.43
     pozdě
    -0.43
    veja
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.06
    Personendaten
    1.06
     betweenstory
    1.02
    
    0.98
     препратки
    0.87
    expandindo
    0.80
     виправивши
    0.77
     pinulongan
    0.76
    Portail
    0.75
     estimés
    0.75
    Activations Density 0.016%

    No Known Activations