© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1629
    Prev
    Next
    INDEX
    Explanations

    the word "be" or forms of "to be."

    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
    Negative Logits
     not
    -1.41
    not
    -1.23
     usually
    -1.20
     also
    -1.19
     being
    -1.19
     already
    -1.16
     often
    -1.12
     always
    -1.09
     now
    -1.05
     never
    -1.02
    POSITIVE LOGITS
    atify
    0.79
    have
    0.75
    friend
    0.69
    HAVE
    0.69
     construed
    0.68
    IActionResult
    0.65
    MultipartFile
    0.65
     Viewed
    0.65
    viewed
    0.64
    useful
    0.63
    Activations Density 0.590%

    No Known Activations