© 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. 16705
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and numerical values related to procedures or methodologies

    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
    AndroidJUnit
    -0.94
     Paglinawan
    -0.85
    RunAsync
    -0.73
    pushFollow
    -0.73
    SOUNDBITE
    -0.72
     linkovi
    -0.70
     onPostExecute
    -0.68
     հղումներ
    -0.61
     Rptr
    -0.61
    aarrggbb
    -0.60
    POSITIVE LOGITS
     Aucun
    0.42
    صال
    0.41
    æn
    0.40
     yng
    0.40
     gelten
    0.39
     system
    0.39
    tool
    0.39
    heids
    0.39
    propri
    0.38
     этому
    0.38
    Activations Density 0.711%

    No Known Activations