© 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. 2-RES-MATRYOSHKA-DC
    7. 5753
    Prev
    Next
    INDEX
    Explanations

    references or mentions of specific named entities, such as people's names or place names

    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
     Lorenzo
    -0.56
     confor
    -0.56
    mfenced
    -0.56
    }}}{\
    -0.56
    เทศ
    -0.54
    Guido
    -0.54
    Gai
    -0.53
     Miet
    -0.52
     Wiener
    -0.52
     Guido
    -0.52
    POSITIVE LOGITS
     Cassidy
    0.88
    CTP
    0.88
     Bash
    0.85
     republics
    0.85
    ThroughAttribute
    0.85
     CTP
    0.85
     Baton
    0.83
     Rodrig
    0.82
     Motta
    0.82
     Saul
    0.81
    Activations Density 1.762%

    No Known Activations