© 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. 274
    Prev
    Next
    INDEX
    Explanations

    mentions of formal language or classifications in descriptions

    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
     Lucius
    -0.56
    gu
    -0.46
     biling
    -0.46
     Tiberius
    -0.46
    äu
    -0.45
     fluo
    -0.45
     relais
    -0.43
     Sully
    -0.42
    ıyors
    -0.42
     Giovanna
    -0.42
    POSITIVE LOGITS
     nor
    1.15
    而是
    0.92
    nor
    0.87
     melainkan
    0.87
     CreateTagHelper
    0.82
    むしろ
    0.82
     sondern
    0.77
     بلکه
    0.75
     Nor
    0.72
     tampoco
    0.70
    Activations Density 2.935%

    No Known Activations