© 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. 3-RES-MATRYOSHKA-DC
    7. 1945
    Prev
    Next
    INDEX
    Explanations

    the word "project"

    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
     Chamb
    -0.64
    antlr
    -0.60
     Constitucional
    -0.60
    čeno
    -0.55
     medios
    -0.54
    ammans
    -0.54
    cetak
    -0.54
     colpo
    -0.53
    InStock
    -0.53
    oinette
    -0.52
    POSITIVE LOGITS
     project
    3.38
     Project
    3.27
     PROJECT
    3.14
     projects
    3.13
    Project
    3.09
    project
    3.03
     Projects
    3.02
    PROJECT
    2.94
    Projects
    2.75
    projects
    2.72
    Activations Density 0.130%

    No Known Activations