© 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. 946
    Prev
    Next
    INDEX
    Explanations

    the word "analysis"

    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
     expéri
    -0.68
    덟
    -0.56
     bū
    -0.55
    EXPERIMENTAL
    -0.54
    Abr
    -0.53
     méri
    -0.52
    一
    -0.52
     experimentally
    -0.52
    ме
    -0.51
     EXPERIMENTAL
    -0.50
    POSITIVE LOGITS
     analysis
    2.72
     Analysis
    2.64
     analyses
    2.59
     Analyses
    2.59
     ANALYSIS
    2.52
    analysis
    2.50
    Analysis
    2.47
    Analyses
    2.45
    ANALYSIS
    2.33
    analyses
    2.28
    Activations Density 0.188%

    No Known Activations