© 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. 3-RES-MATRYOSHKA-DC
    7. 738
    Prev
    Next
    INDEX
    Explanations

    negations and words indicating a lack of something

    oai_token-act-pair · gemini-2.0-flash
    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
     every
    -1.20
     Every
    -1.12
    Every
    -1.10
    every
    -1.05
     EVERY
    -0.94
     Ogni
    -0.90
     ogni
    -0.87
    Ogni
    -0.85
     varje
    -0.83
     Setiap
    -0.82
    POSITIVE LOGITS
     nothing
    1.95
    nothing
    1.91
     none
    1.81
    none
    1.76
    None
    1.72
    Nothing
    1.72
     Nothing
    1.64
     nessuno
    1.64
     ninguno
    1.62
     None
    1.60
    Activations Density 0.246%

    No Known Activations