© 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. 24-RES-MATRYOSHKA-DC
    7. 111
    Prev
    Next
    INDEX
    Explanations

    present and past tense forms of the verb "to be" alongside technical nouns and conjunctions

    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/blocks.24.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.24.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
     ſeveral
    -0.96
     définiti
    -0.94
     Theſe
    -0.91
     auroit
    -0.90
     Monfieur
    -0.90
     Jefus
    -0.89
     purpoſe
    -0.89
     engraçadas
    -0.88
     réalis
    -0.88
     supérieurs
    -0.88
    POSITIVE LOGITS
     taken
    1.09
     made
    1.09
     put
    1.08
     brought
    1.07
     placed
    1.03
     used
    0.97
     sent
    0.93
     kept
    0.91
     introduced
    0.90
     given
    0.89
    Activations Density 6.955%

    No Known Activations