© 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. 2-RES-MATRYOSHKA-DC
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    expressions of disagreement or contradiction

    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
    RectangleBorder
    -0.82
    TagMode
    -0.78
    InjectAttribute
    -0.75
     Normdatei
    -0.75
     Forumite
    -0.74
    وانید
    -0.73
     betweenstory
    -0.72
    adaptiveStyles
    -0.71
    InstrumentedTest
    -0.71
     pinulongan
    -0.70
    POSITIVE LOGITS
     are
    0.47
    ์
    0.46
     were
    0.45
    ins
    0.45
     opérateur
    0.45
    ))
    0.44
     g
    0.43
    事的
    0.43
    вы
    0.42
    制
    0.42
    Activations Density 0.762%

    No Known Activations