© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    the word "benefit" or "benefits"

    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
    bibinfo
    -0.80
    bosis
    -0.69
    BibitemShut
    -0.67
    — 
    -0.60
    Externé
    -0.59
     esternos
    -0.59
     Ia
    -0.58
    tse
    -0.58
    ellery
    -0.58
     contd
    -0.58
    POSITIVE LOGITS
     benefits
    2.22
     benefit
    2.06
     Benefits
    2.02
    benefits
    1.91
    Benefits
    1.91
    Benefit
    1.87
     BENEFITS
    1.87
    benefit
    1.85
     Benefit
    1.81
    BENEFITS
    1.80
    Activations Density 0.629%

    No Known Activations