© 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. 2-RES-MATRYOSHKA-DC
    7. 4891
    Prev
    Next
    INDEX
    Explanations

    references to ATP concentrations and related biochemical measurements

    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
     McPherson
    -0.74
     protoimpl
    -0.65
    tą
    -0.61
    Ruf
    -0.61
     SCS
    -0.60
    ỡng
    -0.59
    cism
    -0.59
    ↕
    -0.59
    Roh
    -0.58
    ttu
    -0.58
    POSITIVE LOGITS
     ATP
    3.27
    ATP
    3.17
     adenosine
    1.44
    enosine
    0.87
     WTA
    0.82
     iParam
    0.70
    ADP
    0.70
    GTP
    0.69
     ADP
    0.68
    NAD
    0.66
    Activations Density 0.003%

    No Known Activations