© 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. 0-RES-MATRYOSHKA-DC
    7. 12504
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" in text

    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
     initComponents
    -0.95
    migrationBuilder
    -0.79
    SOUNDBITE
    -0.75
    TagHelper
    -0.72
     للاسماء
    -0.72
    abestanden
    -0.66
    Datuak
    -0.63
    ziasztok
    -0.60
    Portail
    -0.60
     يتيمه
    -0.60
    POSITIVE LOGITS
    Browsable
    0.63
     GetEnumerator
    0.56
     nostru
    0.56
    ust
    0.55
    MouseAdapter
    0.52
    writeField
    0.52
     colleague
    0.50
     ciência
    0.50
     noemen
    0.50
     rightfully
    0.50
    Activations Density 0.197%

    No Known Activations