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. 15954
    Prev
    Next
    INDEX
    Explanations

    code structure involving method calls and object retrieval

    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
     @"/
    -0.45
    FIGURE
    -0.44
    の一覧
    -0.44
     te
    -0.43
     поду
    -0.43
     case
    -0.43
     function
    -0.43
     box
    -0.43
     pol
    -0.42
    AnchorStyles
    -0.42
    POSITIVE LOGITS
     quæ
    0.80
     Jefus
    0.79
     Roskov
    0.79
     متعلقه
    0.77
     habet
    0.76
    findpost
    0.75
    ponses
    0.74
     houſe
    0.73
    quitous
    0.69
     myſelf
    0.69
    Activations Density 0.099%

    No Known Activations