© 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. 407
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "study", particularly in connection to research

    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
    kai
    -0.60
     *****
    -0.60
    s
    -0.59
    *****
    -0.58
    cfm
    -0.57
     mince
    -0.56
     baseman
    -0.55
    ına
    -0.54
    js
    -0.54
    langle
    -0.54
    POSITIVE LOGITS
     study
    2.83
     Study
    2.69
    study
    2.63
    Study
    2.58
     studies
    2.50
     STUDY
    2.50
    STUDY
    2.48
    studies
    2.34
     Studies
    2.22
     studie
    2.13
    Activations Density 0.668%

    No Known Activations