© 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. 12-RES-MATRYOSHKA-DC
    7. 10287
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and variations of the verb "to 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
     there
    -0.68
     few
    -0.64
     are
    -0.60
     clear
    -0.59
    acionais
    -0.59
     number
    -0.58
    ersen
    -0.55
    segue
    -0.55
     many
    -0.55
     طور
    -0.55
    POSITIVE LOGITS
     CURIAM
    0.88
    uminense
    0.77
    Manfaat
    0.75
    #+#
    0.74
    eseed
    0.72
     neuem
    0.70
    lifies
    0.69
     scl
    0.69
     Anspruch
    0.69
    DataSnapshot
    0.69
    Activations Density 0.025%

    No Known Activations