© 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. 1-RES-MATRYOSHKA-DC
    7. 341
    Prev
    Next
    INDEX
    Explanations

    code snippets related to BIO I/O functions and their control mechanisms

    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
     pédagogique
    -0.74
     commerciales
    -0.71
     către
    -0.70
     sauvages
    -0.68
     fotográfica
    -0.68
     varandra
    -0.68
    存于互联网档案馆
    -0.67
     commerciaux
    -0.67
     ögon
    -0.65
     colectiva
    -0.63
    POSITIVE LOGITS
     int
    4.31
    int
    4.03
     Int
    3.20
    Int
    2.91
    INT
    2.88
     INT
    2.64
     ints
    2.25
    ints
    2.08
    getInt
    1.89
    ∫
    1.88
    Activations Density 0.797%

    No Known Activations