© 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. 2-RES-MATRYOSHKA-DC
    7. 6955
    Prev
    Next
    INDEX
    Explanations

    code size specifications in programming contexts

    oai_token-act-pair · gpt-4.1-nano
    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
     insuffisamment
    -0.65
     eeuw
    -0.61
     Brecht
    -0.60
    ]**
    -0.59
     Fortuna
    -0.57
     Acerca
    -0.57
    thâu
    -0.57
     Nicolson
    -0.56
     Sre
    -0.54
    kwds
    -0.54
    POSITIVE LOGITS
     sizeof
    4.34
    sizeof
    4.16
    offsetof
    1.18
     typeof
    1.05
     nameof
    1.05
    typeof
    0.96
    nameof
    0.94
    setof
    0.85
    +#+#
    0.65
     strlen
    0.64
    Activations Density 0.001%

    No Known Activations