© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2351
    Prev
    Next
    INDEX
    Explanations

    keywords related to systematic reviews and research methodologies in scientific literature

    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
    /**
    -0.50
     Outro
    -0.49
     createSlice
    -0.48
     Zuz
    -0.48
     Вікі
    -0.48
     fars
    -0.48
    Życiorys
    -0.48
     pamamagitan
    -0.48
    Critique
    -0.48
    ờ
    -0.47
    POSITIVE LOGITS
     keywords
    0.85
     keyword
    0.82
    keywords
    0.75
     Keyword
    0.68
     saites
    0.67
    关键字
    0.65
    keyword
    0.65
     Keywords
    0.65
    キーワード
    0.60
    検索
    0.59
    Activations Density 0.211%

    No Known Activations