© 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. 1-RES-MATRYOSHKA-DC
    7. 172
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the verb "to be" in various contexts

    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
    RegistryLite
    -1.05
    Personendaten
    -0.96
    ]--;
    -0.87
    fjspx
    -0.82
     gyhoeddwyd
    -0.82
     Numerade
    -0.82
     Paglinawan
    -0.82
     Lightboxes
    -0.81
     doInBackground
    -0.79
    ThroughAttribute
    -0.79
    POSITIVE LOGITS
     be
    3.66
     Be
    2.45
    Be
    2.42
    be
    2.41
     BE
    1.88
     être
    1.63
    BE
    1.57
    ToBe
    1.49
     soient
    1.47
     быть
    1.45
    Activations Density 1.123%

    No Known Activations