© 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. 11016
    Prev
    Next
    INDEX
    Explanations

    references to colleagues and collaborative relationships

    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
     family
    -0.69
    addContainerGap
    -0.60
    Παραπομπές
    -0.59
     Familien
    -0.57
    marshaller
    -0.56
    sierung
    -0.56
     Family
    -0.54
    retin
    -0.54
    family
    -0.53
     pobla
    -0.52
    POSITIVE LOGITS
     colleague
    1.46
     colleagues
    1.39
     Colleagues
    1.20
     colega
    1.15
     colegas
    1.11
     collègues
    1.11
     collega
    1.05
     Kollegen
    1.02
     classmate
    0.93
     coworker
    0.93
    Activations Density 0.029%

    No Known Activations