© 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. 6-RES-MATRYOSHKA-DC
    7. 951
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express conflict or disagreement, or the absence thereof.

    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
    ntp
    -0.49
    悴
    -0.48
    hastly
    -0.47
    sellors
    -0.47
    RegistryLite
    -0.47
    pagnes
    -0.46
    "}\
    -0.45
    ="">
    -0.45
    }>
    -0.44
    GRANTED
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.80
     nor
    0.74
     anymore
    0.73
    EndContext
    0.69
    CloseOperation
    0.69
    borderSide
    0.67
     preocupes
    0.66
     nici
    0.65
     any
    0.63
     nào
    0.62
    Activations Density 1.828%

    No Known Activations