© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    references to the influence or measurement of specific biochemical agents, particularly related to adenosine levels or activity

    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
     cesse
    -0.69
    voorbeeld
    -0.66
    ioutil
    -0.65
     refroid
    -0.64
     exécut
    -0.63
     alberi
    -0.63
     engraçadas
    -0.63
    didSet
    -0.63
    йся
    -0.61
    MessageTagHelper
    -0.60
    POSITIVE LOGITS
     +/-
    2.03
    +/-
    1.80
     +-
    0.77
     /-
    0.70
    >*/
    0.65
     (...)
    0.65
    rungsseite
    0.64
     Ansch
    0.62
    /////////////
    0.62
    
    0.61
    Activations Density 0.012%

    No Known Activations