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. 14108
    Prev
    Next
    INDEX
    Explanations

    concepts related to standalone films centered on female characters and their roles

    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
    InjectAttribute
    -0.93
     elettrico
    -0.73
    AnchorStyles
    -0.71
     enää
    -0.70
    AccessorTable
    -0.70
    fortawesome
    -0.69
     Normdatei
    -0.68
    aarrggbb
    -0.67
     umana
    -0.64
    AddHtmlAttribute
    -0.64
    POSITIVE LOGITS
     standalone
    0.61
     самостоя
    0.53
     independently
    0.50
     samodziel
    0.50
     independent
    0.49
    alone
    0.48
    independent
    0.47
     Independent
    0.47
    独立
    0.47
     INDEPENDENT
    0.47
    Activations Density 0.192%

    No Known Activations