© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4241
    Prev
    Next
    INDEX
    Explanations

    concepts related to courage and bravery in various contexts

    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
    basicConfig
    -0.69
    Tembelea
    -0.64
     intptr
    -0.60
    timewa
    -0.59
     pleasurable
    -0.59
    .$_
    -0.58
    cians
    -0.57
    }^{+\
    -0.56
    verwijspagina
    -0.54
     harmonious
    -0.54
    POSITIVE LOGITS
     courage
    1.33
     coraggio
    1.20
    Courage
    1.17
     courageous
    1.15
     Courage
    1.13
     bravery
    1.13
     brave
    1.11
     bravely
    1.02
     berani
    0.98
    brave
    0.97
    Activations Density 0.362%

    No Known Activations