© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 898
    Prev
    Next
    INDEX
    Explanations

    phrases that describe or represent entities and their characteristics in a structured manner

    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
     issue
    -0.50
    ЭС
    -0.50
     use
    -0.49
    wik
    -0.48
    Schweizer
    -0.48
     sociaux
    -0.48
     lägga
    -0.48
    issue
    -0.46
     egne
    -0.46
    ьажоргаш
    -0.45
    POSITIVE LOGITS
     represents
    1.17
     representing
    1.17
    represents
    1.14
     Represents
    1.10
     represent
    1.07
     autorytatywna
    1.05
    representing
    1.05
    Represents
    1.03
     Representing
    1.02
     represen
    1.00
    Activations Density 0.881%

    No Known Activations