© 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. 797
    Prev
    Next
    INDEX
    Explanations

    the word "reference" and variations of that word such as "Ref" and "References", possibly within documentation

    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
    EndGlobalSection
    -0.62
     Garn
    -0.58
    ーション
    -0.55
     Lyle
    -0.54
    enumii
    -0.54
    GraphicsUnit
    -0.54
     recessive
    -0.54
     ISD
    -0.53
    EndContext
    -0.53
     Angleterre
    -0.52
    POSITIVE LOGITS
     REF
    1.21
     refs
    1.12
    REF
    1.11
     ref
    1.05
    ref
    1.05
     Ref
    1.04
     Refs
    1.01
    Ref
    0.96
     references
    0.94
     useRef
    0.93
    Activations Density 0.406%

    No Known Activations