© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 248
    Prev
    Next
    INDEX
    Explanations

    boolean logic keywords such as true, false, bool, and null

    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
     AssemblyCompany
    -0.64
     <>",
    -0.63
     wichtigste
    -0.61
     Dichter
    -0.59
    __*/
    -0.59
    rest
    -0.58
    Activités
    -0.58
    োগ
    -0.58
     îles
    -0.58
     territoires
    -0.58
    POSITIVE LOGITS
     true
    2.69
     True
    2.59
    True
    2.55
    true
    2.44
     TRUE
    2.33
    TRUE
    2.28
    False
    1.99
     False
    1.93
     false
    1.92
    false
    1.88
    Activations Density 0.710%

    No Known Activations