© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    code patterns related to boolean variables

    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
     Obtenez
    -0.70
    HasKey
    -0.66
    انظر
    -0.65
     Kindern
    -0.63
     Gogh
    -0.60
     immobilier
    -0.60
    ղ
    -0.59
     volks
    -0.59
    ագրություններ
    -0.58
     Ordnung
    -0.57
    POSITIVE LOGITS
    boolean
    2.64
     boolean
    2.56
    Boolean
    1.77
     Boolean
    1.73
    oolean
    1.49
     BOOLEAN
    1.42
    BOOLEAN
    1.36
    BOOL
    1.09
     BOOL
    1.02
    getBoolean
    0.83
    Activations Density 0.014%

    No Known Activations