© 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. 432
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in its various forms.

    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
    RegistryLite
    -1.10
    Personendaten
    -1.07
     lädt
    -0.93
    expandindo
    -0.92
     الرياضيه
    -0.90
     Anis
    -0.88
     itſelf
    -0.88
    Olvid
    -0.84
     CURIAM
    -0.84
    UnusedPrivate
    -0.82
    POSITIVE LOGITS
     be
    2.28
    Be
    1.63
     Be
    1.63
    be
    1.51
     BE
    1.14
     être
    1.07
    toBe
    1.04
    ToBe
    1.04
     been
    1.01
    tobe
    0.99
    Activations Density 1.679%

    No Known Activations