© 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. 0-RES-MATRYOSHKA-DC
    7. 12737
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values related to stoichiometry or standardized measurement parameters

    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
    ayaquil
    -0.67
    OGND
    -0.59
    avadoc
    -0.54
    cons
    -0.54
    Cons
    -0.52
    rodalom
    -0.52
    elser
    -0.50
    relser
    -0.49
    ुष
    -0.48
     Ede
    -0.47
    POSITIVE LOGITS
    SBATCH
    0.79
     stoichio
    0.76
     Atkins
    0.73
    defineProperty
    0.71
    förs
    0.68
    createClass
    0.68
     Decker
    0.66
    coe
    0.65
     Coe
    0.65
    ptid
    0.63
    Activations Density 0.079%

    No Known Activations