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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6357
    Prev
    Next
    INDEX
    Explanations

    formal mathematical expressions and terminology

    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
    MemoryWarning
    -0.73
     Chwiliwch
    -0.72
     EconPapers
    -0.72
    tvguidetime
    -0.71
    CreateModel
    -0.59
    ]")]
    -0.58
    posedge
    -0.57
    complexContent
    -0.57
     MainAxisSize
    -0.57
     متعلقه
    -0.57
    POSITIVE LOGITS
    Referanser
    0.52
    chule
    0.52
    NGC
    0.51
     Bibliothe
    0.51
     bough
    0.51
    יע
    0.49
     nacionais
    0.49
    ี
    0.47
     Militar
    0.46
     proceed
    0.46
    Activations Density 0.300%

    No Known Activations