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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1085
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations beginning in "SIG" or "IG"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     שוליים
    -1.02
     InputDecoration
    -0.65
    存于互联网档案馆
    -0.63
     Obrador
    -0.62
     Catho
    -0.62
     Penh
    -0.58
    expandindo
    -0.56
     ditu
    -0.55
     Rov
    -0.54
     caseros
    -0.54
    POSITIVE LOGITS
     SIG
    0.85
     SID
    0.77
     SIA
    0.76
     Sime
    0.74
     SEÑ
    0.74
     Sidd
    0.69
     SIS
    0.68
     Sib
    0.67
     Sinha
    0.66
     slings
    0.66
    Activations Density 0.911%

    No Known Activations