© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5423
    Prev
    Next
    INDEX
    Explanations

    words related to promises and commitments

    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
    kuuta
    -0.83
    évaluateur
    -0.71
     Hayek
    -0.67
    intios
    -0.65
    fjspx
    -0.65
    ILayout
    -0.60
     conci
    -0.58
     рук
    -0.57
    chico
    -0.57
    tanleria
    -0.56
    POSITIVE LOGITS
     promise
    1.86
     Promise
    1.85
     promises
    1.79
    Promise
    1.74
     Promises
    1.74
    promise
    1.66
    Promises
    1.60
     promised
    1.58
     promessa
    1.48
    promises
    1.47
    Activations Density 0.121%

    No Known Activations