© 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. 2-RES-MATRYOSHKA-DC
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be."

    oai_token-act-pair · gpt-4.1-nano
    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
    MigrationBuilder
    -0.84
     ProtoMessage
    -0.71
    NOPQRST
    -0.64
     برانيه
    -0.60
    PreferredItem
    -0.59
    GLOBALS
    -0.59
     оригіналу
    -0.59
    ervlak
    -0.58
    WithIOException
    -0.58
     NgModule
    -0.57
    POSITIVE LOGITS
     Be
    1.35
     be
    1.33
    Be
    1.24
     BE
    0.90
    be
    0.90
     beryllium
    0.66
    beto
    0.64
     possano
    0.63
    anskje
    0.62
     Beasley
    0.62
    Activations Density 0.047%

    No Known Activations