© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    the word "corresponding"

    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
     صوتيه
    -0.79
    AsUp
    -0.78
     Uniti
    -0.74
    newUser
    -0.65
    XmlType
    -0.63
    kwds
    -0.62
    IonicModule
    -0.62
     newUser
    -0.61
     jadx
    -0.61
     Glaser
    -0.61
    POSITIVE LOGITS
     corresponding
    2.59
    corresponding
    2.50
     correspond
    2.23
     Corresponding
    2.19
     corresponds
    2.13
     correspondant
    2.09
    Corresponding
    2.02
     corrispond
    1.98
     corresponded
    1.96
     Correspond
    1.86
    Activations Density 0.111%

    No Known Activations