© 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. 877
    Prev
    Next
    INDEX
    Explanations

    references to quantities or comparisons indicating a smaller amount or degree

    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
    DockStyle
    -0.58
    gdx
    -0.58
    jstor
    -0.54
     Small
    -0.53
    Small
    -0.52
    gaver
    -0.50
     Larger
    -0.49
    Etymology
    -0.49
     SwitchCompat
    -0.48
    Throwable
    -0.48
    POSITIVE LOGITS
     less
    3.64
     Less
    3.47
    Less
    3.45
    less
    3.17
     LESS
    3.03
    LESS
    2.81
     moins
    2.70
     menos
    2.56
     weniger
    2.31
     lefs
    2.25
    Activations Density 0.320%

    No Known Activations