Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 9221
    Prev
    Next
    INDEX
    Explanations

    descriptive words conveying positive emotions and vibrant imagery

    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
     chłod
    -0.56
     Stalker
    -0.55
     Sturgeon
    -0.52
     torr
    -0.52
    knecht
    -0.52
     pensieri
    -0.51
    тература
    -0.51
     longues
    -0.51
     médicaux
    -0.51
    Ӏ
    -0.51
    POSITIVE LOGITS
     upbeat
    0.93
     cheerful
    0.92
     optimism
    0.89
     vibrant
    0.89
     energetic
    0.88
     lively
    0.87
     exuberant
    0.85
     buoyant
    0.84
     cheery
    0.83
     alegre
    0.82
    Activations Density 0.072%

    No Known Activations