© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 282
    Prev
    Next
    INDEX
    Explanations

    phrases related to existence or presence, particularly focusing on the verb "be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anis
    -0.91
    hdashline
    -0.85
    expandindo
    -0.82
    RegistryLite
    -0.81
    Personendaten
    -0.81
    Olvid
    -0.80
     Isi
    -0.79
     Jefus
    -0.79
     Forman
    -0.79
    PathVariable
    -0.77
    POSITIVE LOGITS
     be
    1.19
    Be
    1.02
     Be
    0.98
    be
    0.96
    ReusableCell
    0.89
     Bevan
    0.73
     Audiodateien
    0.71
     Belich
    0.71
     BE
    0.71
    ={()=>
    0.69
    Activations Density 1.319%

    No Known Activations