© 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. 20856
    Prev
    Next
    INDEX
    Explanations

    references to creativity and creative expression

    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
     betweenstory
    -0.77
     Brock
    -0.71
    +#+
    -0.69
    Brock
    -0.69
    ġġ
    -0.65
    ται
    -0.63
     DbType
    -0.63
    bul
    -0.62
     surla
    -0.62
    wachung
    -0.62
    POSITIVE LOGITS
    Creative
    1.18
     Creative
    1.15
     Creativity
    1.01
     creativity
    0.99
     creatively
    0.97
     creativo
    0.96
     creative
    0.94
    Creativity
    0.91
    creative
    0.91
     creativa
    0.88
    Activations Density 0.002%

    No Known Activations