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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 580
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a central theme or main focus

    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
     DbType
    -0.65
     δικ
    -0.64
     Methuen
    -0.62
    nb
    -0.59
     FORMA
    -0.58
     commissioner
    -0.58
     dår
    -0.57
    ppar
    -0.56
    CodeDom
    -0.56
    ன்ற
    -0.54
    POSITIVE LOGITS
     focus
    2.06
     focuses
    1.78
     Focus
    1.73
     focusing
    1.73
     focused
    1.72
    focus
    1.68
    Focus
    1.66
     FOCUS
    1.64
     fokus
    1.63
     emphasis
    1.61
    Activations Density 0.648%

    No Known Activations