© 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. 12-RES-MATRYOSHKA-DC
    7. 20834
    Prev
    Next
    INDEX
    Explanations

    terminology related to cellular biology and medical research

    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
    中略
    -0.51
     kanya
    -0.47
    šanai
    -0.46
    šanu
    -0.44
     odkazy
    -0.39
    Datuak
    -0.39
     stället
    -0.39
     izvē
    -0.38
    nivå
    -0.38
     szüks
    -0.38
    POSITIVE LOGITS
    AccessorTable
    0.91
    writeFieldEnd
    0.84
    fjspx
    0.82
    ScopeManager
    0.81
    expandindo
    0.79
    CppCodeGen
    0.76
    complexType
    0.75
     فريبيس
    0.75
    antMatchers
    0.75
     nahilalakip
    0.74
    Activations Density 0.649%

    No Known Activations