© 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. 537
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "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
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.64
     designed
    -0.60
     able
    -0.58
     suitable
    -0.56
     prepared
    -0.54
     unfit
    -0.54
     produced
    -0.52
    ustomed
    -0.52
     capable
    -0.51
    phite
    -0.51
    POSITIVE LOGITS
     mitigated
    0.80
     minimized
    0.70
     exemplified
    0.70
     evidenced
    0.69
    achieved
    0.69
    IsContent
    0.68
     reflected
    0.67
     underscored
    0.66
     aided
    0.66
     maximized
    0.65
    Activations Density 0.821%

    No Known Activations