© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12022
    Prev
    Next
    INDEX
    Explanations

    numerical data patterns or values related to progress indicators, measurements, or scores within text

    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
    ueuse
    -0.71
    ')):
    -0.70
    styleType
    -0.62
    saraba
    -0.61
    ')")
    -0.61
     Chwiliwch
    -0.60
     pinulongan
    -0.60
     @"/
    -0.59
    toThrow
    -0.59
    Здра
    -0.59
    POSITIVE LOGITS
     Benson
    0.88
    DataURL
    0.82
    xyz
    0.77
    %">
    0.76
    azar
    0.74
    NOPQRST
    0.68
     fears
    0.68
    cdnjs
    0.67
    atories
    0.65
     trout
    0.65
    Activations Density 0.080%

    No Known Activations