© 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. 5788
    Prev
    Next
    INDEX
    Explanations

    parenthetical year citations in academic papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx

    parentheses in text

    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
    CodeDom
    -0.68
    IsMutable
    -0.67
     Ovid
    -0.64
    uegos
    -0.62
     Audiodateien
    -0.61
    umab
    -0.60
     Sinter
    -0.60
     lobsters
    -0.59
    complexType
    -0.59
    httphttps
    -0.59
    POSITIVE LOGITS
    Datuak
    0.69
     "..\..\..\
    0.65
    alada
    0.55
     "..\..\
    0.52
     Richard
    0.51
    HEET
    0.50
     verzorg
    0.49
    PerformLayout
    0.48
    plaatst
    0.48
    assins
    0.47
    Activations Density 0.017%

    No Known Activations