© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly related to people and places

    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
    UnusedPrivate
    -0.81
    a
    -0.74
    liothèque
    -0.69
    Kariera
    -0.66
    edale
    -0.64
     kasarigan
    -0.63
    o
    -0.63
    collate
    -0.59
    på
    -0.59
    subsubsection
    -0.58
    POSITIVE LOGITS
     Erm
    1.04
    mers
    1.01
     JAM
    1.01
    HAM
    0.99
     Dm
    0.97
    tm
    0.96
     BBM
    0.96
     Rami
    0.94
     HEM
    0.94
     JIM
    0.94
    Activations Density 1.295%

    No Known Activations