© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12174
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    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
    مصادر
    -0.48
    stdafx
    -0.46
    yntax
    -0.45
    #+#
    -0.45
     kont
    -0.44
     failure
    -0.44
    DebuggerNonUser
    -0.43
    횟
    -0.43
     Hai
    -0.42
    Coast
    -0.42
    POSITIVE LOGITS
     AssemblyCompany
    0.75
    SourceChecksum
    0.63
    InSection
    0.63
    AnchorTagHelper
    0.60
     समीक्षाएं
    0.60
    arXiv
    0.60
    ikations
    0.58
    InitVars
    0.58
     hanem
    0.57
    WaitGroup
    0.57
    Activations Density 0.010%

    No Known Activations