© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to parameters and their estimation

    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
    GraphicsUnit
    -0.63
     FetchType
    -0.59
     stories
    -0.57
     Majefty
    -0.55
    WriteTagHelper
    -0.54
    corer
    -0.54
     "/";
    -0.52
    >";
    -0.50
     ".";
    -0.50
     streak
    -0.50
    POSITIVE LOGITS
     parameter
    3.89
     parameters
    3.78
     Parameters
    3.72
     Parameter
    3.61
    parameter
    3.38
    parameters
    3.33
    Parameters
    3.20
    Parameter
    3.17
     PARAMETERS
    3.02
     PARAMETER
    2.98
    Activations Density 0.145%

    No Known Activations