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. 31735
    Prev
    Next
    INDEX
    Explanations

    references to a specific acronym or term, particularly related to a certain political or organizational context

    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
     Bally
    -0.75
    Попис
    -0.73
    istani
    -0.67
    Хьажоргаш
    -0.66
    bellar
    -0.66
     برانيه
    -0.66
     Nassau
    -0.66
    rungsseite
    -0.65
     متعلقه
    -0.64
    .…
    -0.64
    POSITIVE LOGITS
     dap
    1.48
     Dap
    1.48
    Dap
    1.48
    DAP
    1.36
     DAP
    1.33
    dap
    1.21
     ]];
    0.78
     Lakeside
    0.70
    hnia
    0.69
    '));
    
    0.65
    Activations Density 0.000%

    No Known Activations