© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5789
    Prev
    Next
    INDEX
    Explanations

    references to figures or panels in visual or data representations

    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
    >-->
    -0.67
    ']?>
    -0.65
     Zaragoza
    -0.65
    켜
    -0.65
    inose
    -0.64
     Dha
    -0.63
     Fortaleza
    -0.63
     HttpResponse
    -0.61
     $"{
    -0.60
     dece
    -0.59
    POSITIVE LOGITS
     panels
    1.70
     Panels
    1.67
    panels
    1.63
     Panel
    1.63
    Panels
    1.58
     PANEL
    1.49
    PANEL
    1.49
     panel
    1.48
    panel
    1.46
    Panel
    1.44
    Activations Density 0.024%

    No Known Activations