© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 4087
    Prev
    Next
    INDEX
    Explanations

    passages of text expressing a conclusion or summary

    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
    Thus
    -1.37
     Thus
    -1.33
    ']))
    
    -0.82
     thus
    -0.76
    thus
    -0.76
    ]))
    
    -0.76
    دانشنامهٔ
    -0.73
    ]));
    
    -0.71
     Ainsi
    -0.71
    featureID
    -0.67
    POSITIVE LOGITS
     therefore
    1.34
     Therefore
    1.23
    Therefore
    1.22
    therefore
    1.18
    Поэтому
    1.02
     Daarom
    0.95
     Deshalb
    0.94
     daarom
    0.88
     therefor
    0.87
     Поэтому
    0.84
    Activations Density 0.028%

    No Known Activations