© 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. 1600
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental controls and comparisons in scientific studies

    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
     ſever
    -0.67
     ſte
    -0.63
     fevere
    -0.62
     Eſ
    -0.59
    tenham
    -0.56
    ußt
    -0.56
     faſt
    -0.54
    TERN
    -0.54
     Offen
    -0.52
     pleaſure
    -0.52
    POSITIVE LOGITS
    EDEFAULT
    0.78
     utafitiHapana
    0.77
    principalTable
    0.71
    ViewImports
    0.68
     typelib
    0.67
     achtergrond
    0.62
    SharedCtor
    0.61
     bakgrund
    0.60
     normalen
    0.57
    ]")]
    0.57
    Activations Density 1.349%

    No Known Activations