© 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. 2-RES-MATRYOSHKA-DC
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals involved in a context, such as victims, defendants, and other related persons

    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
    PerformLayout
    -0.77
     Dyck
    -0.73
    expandindo
    -0.69
     Ira
    -0.69
    urlopen
    -0.69
     Span
    -0.68
     Bard
    -0.66
    FilterChain
    -0.66
    URLException
    -0.66
    Bard
    -0.65
    POSITIVE LOGITS
    __":
    0.96
     Collingwood
    0.81
     cubo
    0.70
    __':
    0.70
    __":
    0.68
     Natal
    0.67
    Ư
    0.67
     Vict
    0.65
     Ontario
    0.65
     Newark
    0.64
    Activations Density 1.682%

    No Known Activations