© 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. 3861
    Prev
    Next
    INDEX
    Explanations

    references to placebo in clinical trial contexts

    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
    ainte
    -0.69
    MAXN
    -0.65
    ]),
    -0.62
    antenimiento
    -0.60
    uiente
    -0.60
    residents
    -0.59
    "]),
    -0.59
    canakan
    -0.59
     profiling
    -0.58
     Profiling
    -0.58
    POSITIVE LOGITS
     placebo
    1.63
     Placebo
    1.39
    Personensuche
    0.73
    enumi
    0.69
    IUrlHelper
    0.66
    aarrggbb
    0.66
    Geplaatst
    0.64
    PRNewswire
    0.60
    dobe
    0.60
    PMailer
    0.57
    Activations Density 0.005%

    No Known Activations