© 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. 6-RES-MATRYOSHKA-DC
    7. 623
    Prev
    Next
    INDEX
    Explanations

    the word "first", sometimes followed by a verb of description

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.96
     &___
    -0.94
    XmlAccessorType
    -0.90
     NSCoder
    -0.90
    StoryboardSegue
    -0.87
     pinulongan
    -0.86
     للاسماء
    -0.85
    rungsseite
    -0.85
    tagHelperRunner
    -0.84
    Geplaatst
    -0.81
    POSITIVE LOGITS
    abord
    1.12
    Firstly
    1.11
    unächst
    1.10
     Firstly
    1.04
    Primero
    1.03
    pierw
    1.03
     firstly
    0.99
     First
    0.98
    First
    0.98
    まず
    0.98
    Activations Density 0.641%

    No Known Activations