© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5807
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "modern."

    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
    новниш
    -0.71
    nestjs
    -0.69
    asticity
    -0.69
     Skyscanner
    -0.68
    DataMember
    -0.65
     nulle
    -0.64
    labelledby
    -0.60
    Geplaatst
    -0.59
    alamualaikum
    -0.59
    addGap
    -0.59
    POSITIVE LOGITS
    modern
    1.48
     modern
    1.36
     Modern
    1.34
    Modern
    1.31
    MODERN
    1.30
     MODERN
    1.28
     moderne
    1.27
     moderni
    1.24
     modernity
    1.20
    moderne
    1.18
    Activations Density 0.022%

    No Known Activations