© 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. 794
    Prev
    Next
    INDEX
    Explanations

    code syntax, specifically parenthesis, brackets, curly braces, ampersands, and exclamation points

    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
     O
    -0.69
     =
    -0.68
     Rosenthal
    -0.67
     string
    -0.66
     os
    -0.66
     P
    -0.65
     U
    -0.65
     A
    -0.65
     is
    -0.65
     x
    -0.65
    POSITIVE LOGITS
    principalColumn
    1.02
     themſelves
    0.99
     Shakspeare
    0.94
     Cæsar
    0.94
     poffible
    0.92
     Houſe
    0.91
     itſelf
    0.91
     leſs
    0.90
     ſeveral
    0.90
     doubtnut
    0.90
    Activations Density 0.541%

    No Known Activations