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. 25869
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to rights, preservation, and population dynamics in governance 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
    Itoa
    -0.49
    ंदीखरीदारी
    -0.46
    SizeF
    -0.43
     McGee
    -0.42
    richTextPanel
    -0.42
     ơn
    -0.42
    Moda
    -0.40
    tı
    -0.40
    Симпто
    -0.39
    again
    -0.39
    POSITIVE LOGITS
     فريبيس
    0.70
    </tfoot>
    0.70
     الرياضيه
    0.69
    XmlAccessType
    0.69
     kasarigan
    0.68
    Cyfeiriadau
    0.65
    UTERS
    0.63
     ویکی‌آمباردا
    0.62
     الحره
    0.61
    numerusform
    0.59
    Activations Density 0.009%

    No Known Activations