© 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. 11168
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals and their affiliations in news articles

    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
     newspapers
    -0.45
     AspNetCore
    -0.45
     ujednoznacz
    -0.42
    ]-->
    -0.42
    Eloquent
    -0.41
    TextSpan
    -0.41
    gonic
    -0.41
    참고
    -0.40
    WithEmail
    -0.40
     Anya
    -0.40
    POSITIVE LOGITS
    Tikang
    0.73
    transQ
    0.72
    قایناقلار
    0.67
    "])
    0.63
    ništ
    0.61
     '\\;'
    0.59
    RegressionTest
    0.58
     समीक्षाओं
    0.57
    }))
    0.56
     <=",
    0.56
    Activations Density 0.022%

    No Known Activations