© 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. 21554
    Prev
    Next
    INDEX
    Explanations

    conjunctions and certain coordinating phrases

    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
    DeleteBehavior
    -0.73
    MockMvc
    -0.71
    AnchorStyles
    -0.64
    évaluateur
    -0.63
    SequentialGroup
    -0.62
    numerusform
    -0.61
    tagext
    -0.61
    RenderAtEndOf
    -0.60
    HasForeignKey
    -0.59
    LogFactory
    -0.57
    POSITIVE LOGITS
    endencia
    0.60
     "");
    0.59
    
    0.57
     nahilalakip
    0.55
    endale
    0.54
    ahren
    0.52
    ()}}
    0.52
    lidays
    0.51
    őtt
    0.51
     Gans
    0.51
    Activations Density 0.019%

    No Known Activations