© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    negative adverbs and past tense verbs

    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
    ValueStyle
    -0.94
    TagMode
    -0.92
    InstrumentedTest
    -0.77
     vnto
    -0.75
    SequentialGroup
    -0.75
     revanche
    -0.75
    ίδ
    -0.74
    makeConstraints
    -0.74
    Cubit
    -0.74
     estekak
    -0.73
    POSITIVE LOGITS
     never
    2.95
     Never
    2.75
    never
    2.73
    Never
    2.69
     NEVER
    2.55
    NEVER
    2.52
     nunca
    2.11
     ever
    2.02
     EVER
    1.97
     Nunca
    1.96
    Activations Density 0.261%

    No Known Activations