© 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. 2-RES-MATRYOSHKA-DC
    7. 7731
    Prev
    Next
    INDEX
    Explanations

    references to Hellinger distance calculations or bounds

    oai_token-act-pair · gpt-4.1-nano
    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
    aughey
    -0.61
     Chappell
    -0.57
     hospod
    -0.54
    Primal
    -0.53
    $_['
    -0.52
     együtt
    -0.52
     munka
    -0.50
    паковка
    -0.49
     акаде
    -0.49
    upuesto
    -0.47
    POSITIVE LOGITS
    inger
    4.19
    INGER
    3.23
    ingers
    3.03
    ingen
    1.58
    INGEN
    1.25
    inge
    1.08
    ringer
    1.05
    INGE
    1.05
    nger
    1.00
     Normdatei
    0.99
    Activations Density 0.004%

    No Known Activations