© 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. 765
    Prev
    Next
    INDEX
    Explanations

    the word "depending" or "dependent" along with the word "on" and the word "the"

    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
    brochen
    -0.55
    illan
    -0.55
     Al
    -0.54
    zani
    -0.54
     “
    -0.50
     re
    -0.49
     weg
    -0.49
     
    -0.48
     PLoS
    -0.47
    EMPT
    -0.47
    POSITIVE LOGITS
     depending
    1.28
    depending
    1.25
     depends
    1.16
     Depends
    1.13
    Depending
    1.12
     Depending
    1.10
    depends
    1.10
    Depends
    1.10
     depende
    1.07
     whether
    1.05
    Activations Density 0.629%

    No Known Activations