© 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. 205
    Prev
    Next
    INDEX
    Explanations

    expressions of hypothetical situations or conditional statements

    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
     бывают
    -0.65
     been
    -0.59
    ています
    -0.59
    良し
    -0.58
    ことがあります
    -0.57
     اوم
    -0.57
    assertAll
    -0.57
    []>(
    -0.57
    こともあります
    -0.56
     ollut
    -0.56
    POSITIVE LOGITS
     would
    3.78
    would
    3.48
     Would
    3.28
    Would
    3.22
     WOULD
    3.16
     wouldn
    2.08
     würde
    1.93
    wouldn
    1.93
     wouldnt
    1.88
     wou
    1.82
    Activations Density 0.379%

    No Known Activations