© 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. 18-RES-MATRYOSHKA-DC
    7. 654
    Prev
    Next
    INDEX
    Explanations

    language related to performing a study or experiment, especially about human participation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     nonatomic
    -0.58
    ">\
    -0.57
    avadoc
    -0.54
     focusing
    -0.53
     defaultstate
    -0.52
    zic
    -0.51
     ditu
    -0.50
    igshid
    -0.50
    accharides
    -0.49
    Personensuche
    -0.49
    POSITIVE LOGITS
     participation
    2.08
     participate
    2.06
     participates
    1.91
     Participation
    1.90
     participating
    1.87
    particip
    1.84
    Participating
    1.83
     PARTICIP
    1.82
    participation
    1.81
     participated
    1.80
    Activations Density 1.829%

    No Known Activations