© 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. 3-RES-MATRYOSHKA-DC
    7. 1960
    Prev
    Next
    INDEX
    Explanations

    the word "second" or "third"

    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
    ubernur
    -0.79
    th
    -0.76
    Referències
    -0.69
    SourceChecksum
    -0.65
     Baillargeon
    -0.65
    
    -0.64
    TagMode
    -0.64
    ths
    -0.63
    MigrationBuilder
    -0.63
    Referencies
    -0.61
    POSITIVE LOGITS
     second
    2.05
    Second
    1.95
    second
    1.91
     SECOND
    1.87
     Second
    1.85
    SECOND
    1.79
     seconde
    1.55
     seconds
    1.48
     segundo
    1.42
    segundo
    1.35
    Activations Density 0.166%

    No Known Activations