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. 15746
    Prev
    Next
    INDEX
    Explanations

    instances of betrayal and deception among characters or teams

    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
    CodedInputStream
    -0.64
    gdala
    -0.61
    NewGuid
    -0.51
     axillary
    -0.50
    endphp
    -0.49
    cần
    -0.47
     Xunit
    -0.47
    Observed
    -0.47
    énario
    -0.46
    EQUAL
    -0.46
    POSITIVE LOGITS
     Judas
    0.63
     betraying
    0.62
     betrayal
    0.60
     traitor
    0.60
     betray
    0.59
     betrayed
    0.58
    Rüyada
    0.57
    叛
    0.57
     dön
    0.55
    rungsseite
    0.54
    Activations Density 0.215%

    No Known Activations