© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent crimes and related criminal acts

    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
    ✭✭
    -0.68
     זו
    -0.54
    rich
    -0.49
    hfill
    -0.48
    insics
    -0.48
    net
    -0.47
     ldc
    -0.47
    >[]
    -0.47
    zwischen
    -0.47
     least
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.93
     ExecuteAsync
    0.86
    DockStyle
    0.82
    +#+#
    0.81
     AssemblyCompany
    0.80
    Билгалдахарш
    0.79
     '\\;'
    0.78
    amaño
    0.74
     فريبيس
    0.74
    Geplaatst
    0.74
    Activations Density 0.104%

    No Known Activations