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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 235
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making and choices

    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
    ViewFeatures
    -0.91
    ecake
    -0.79
    ocumented
    -0.75
    wareness
    -0.71
    Pratique
    -0.70
     Audiodateien
    -0.69
    documented
    -0.69
     }}"></
    -0.68
    aderie
    -0.68
     MessageBoxIcon
    -0.67
    POSITIVE LOGITS
     choice
    1.77
     choices
    1.62
     Choice
    1.59
     Choosing
    1.57
     choosing
    1.54
     choose
    1.52
     Choices
    1.52
     chooses
    1.51
     CHOICE
    1.50
     chosen
    1.49
    Activations Density 1.500%

    No Known Activations