© 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. 3-RES-MATRYOSHKA-DC
    7. 3453
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "first time"

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hematical
    -0.82
     doubtnut
    -0.66
    oys
    -0.65
     Gees
    -0.61
     times
    -0.60
    canActivate
    -0.58
    ophageal
    -0.58
     Ged
    -0.57
    PullParser
    -0.56
    endwhile
    -0.56
    POSITIVE LOGITS
     MainAxisSize
    0.72
     nowo
    0.69
    ClientSize
    0.66
     nouve
    0.65
     впервые
    0.63
    脚注の使い方
    0.61
     baru
    0.60
    fresh
    0.60
     erstmals
    0.60
     úrov
    0.59
    Activations Density 0.018%

    No Known Activations