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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13650
    Prev
    Next
    INDEX
    Explanations

    references to a specific gene knockout, often with a numerical or symbolic designation

    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
    المناصب
    -0.69
    fromnode
    -0.63
    RegressionTest
    -0.62
    كويكب
    -0.60
    unhofer
    -0.59
    Jeografia
    -0.59
     ModelExpression
    -0.59
     autorytatywna
    -0.56
     incomplète
    -0.56
     кӀ
    -0.56
    POSITIVE LOGITS
     Knockout
    3.06
     knockout
    2.86
     KO
    0.98
    KO
    0.75
     blackout
    0.65
     Blackout
    0.62
     Outer
    0.54
    CORBA
    0.54
    tener
    0.53
     Pana
    0.52
    Activations Density 0.001%

    No Known Activations