© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16548
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or values associated with web elements or errors in a programming 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
    ValueStyle
    -0.76
    ঙ্গ
    -0.57
    awtextra
    -0.51
    rawQuery
    -0.51
    নে
    -0.49
    ctez
    -0.47
    DataSnapshot
    -0.47
    TagHelper
    -0.45
    lk
    -0.45
     &___
    -0.44
    POSITIVE LOGITS
    __':
    0.67
    دانشنامهٔ
    0.67
    AddHtmlAttribute
    0.66
    createComponent
    0.65
     AssemblyCompany
    0.65
     ImportError
    0.64
     ويكيميديا
    0.63
    KEYCODE
    0.63
     végétale
    0.62
     الحره
    0.62
    Activations Density 0.012%

    No Known Activations