© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15216
    Prev
    Next
    INDEX
    Explanations

    references to personal responsibility, specific incidents, or past events

    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
    WebElementEntity
    -0.70
    ValueStyle
    -0.68
     ostavi
    -0.64
     VizieR
    -0.62
    بوابة
    -0.60
    contentLoaded
    -0.59
    TableAdapter
    -0.59
    StoryboardSegue
    -0.58
     kasarigan
    -0.56
     "));
    -0.56
    POSITIVE LOGITS
     hadn
    2.91
     habían
    0.74
     Había
    0.71
     havia
    0.69
    Tikang
    0.66
    Biographie
    0.60
     communs
    0.59
     había
    0.57
     Sosten
    0.57
     hasn
    0.56
    Activations Density 0.001%

    No Known Activations