© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 1064
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
    BeginInit
    -0.68
    исленность
    -0.62
    WireFormatLite
    -0.56
     dor
    -0.56
    󠁴
    -0.54
     comuniques
    -0.53
     <>",
    -0.52
    спонд
    -0.50
     '-';
    -0.50
     {}),
    -0.49
    POSITIVE LOGITS
     regex
    1.25
     match
    1.23
     Match
    1.21
     Pattern
    1.20
     pattern
    1.20
    Pattern
    1.19
    regex
    1.17
     Regex
    1.15
    Match
    1.15
     Matches
    1.13
    Activations Density 0.746%

    No Known Activations