© 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. 9257
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "academic" in various contexts

    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
    Negative Logits
     kasarigan
    -0.92
    RenderAtEndOf
    -0.89
     mergeFrom
    -0.78
    rouvez
    -0.73
    Tes
    -0.69
    %)$
    -0.69
     !}
    -0.68
     borough
    -0.68
     !'
    -0.68
     Chet
    -0.67
    POSITIVE LOGITS
    Academics
    1.20
     Aca
    1.09
     academics
    1.06
     Academic
    0.89
    academic
    0.85
    demics
    0.82
     académico
    0.80
    ians
    0.79
     academic
    0.78
     ACADEM
    0.77
    Activations Density 0.007%

    No Known Activations