© 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. 19938
    Prev
    Next
    INDEX
    Explanations

    words related to companionship and 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
    numerusform
    -0.78
    orescence
    -0.74
     Modesto
    -0.73
     Bartol
    -0.73
     irri
    -0.73
     informática
    -0.71
    Rico
    -0.70
    yscy
    -0.69
     consommateurs
    -0.67
     OnInit
    -0.64
    POSITIVE LOGITS
     Companion
    1.76
     companion
    1.71
    companion
    1.66
     companions
    1.58
    Companion
    1.49
     Companions
    1.38
     COMPAN
    1.31
    Compan
    1.25
     companionship
    1.23
     compagn
    1.05
    Activations Density 0.001%

    No Known Activations