© 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. 1-RES-MATRYOSHKA-DC
    7. 1252
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical or quantifiable measurements, especially those involving quantities, sizes, or amounts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -1.23
    ^(@)
    -1.02
     Theſe
    -1.02
    haustible
    -1.00
     Monfieur
    -0.93
    GHIJKLM
    -0.93
    bibfield
    -0.83
     myſelf
    -0.82
     themſelves
    -0.78
     Jefus
    -0.77
    POSITIVE LOGITS
    of
    1.04
    for
    0.99
    to
    0.88
    with
    0.83
    by
    0.81
    and
    0.79
    OF
    0.79
    from
    0.79
    at
    0.77
    in
    0.75
    Activations Density 3.666%

    No Known Activations