© 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. 2-RES-MATRYOSHKA-DC
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    expressions related to negative test results or negative outcomes

    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
    posi
    -0.64
     dummy
    -0.61
    dummy
    -0.60
    Dummy
    -0.60
     polymorphism
    -0.59
     Conroy
    -0.57
     تضيفلها
    -0.57
    positi
    -0.56
    ordnen
    -0.56
    TextAppearance
    -0.55
    POSITIVE LOGITS
     negative
    1.89
     Negative
    1.78
    negative
    1.77
    Negative
    1.68
    NEGATIVE
    1.56
     negatives
    1.48
     NEGATIVE
    1.46
     négatif
    1.37
     negativo
    1.36
     negativos
    1.27
    Activations Density 0.026%

    No Known Activations