© 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. 1-RES-MATRYOSHKA-DC
    7. 754
    Prev
    Next
    INDEX
    Explanations

    code snippets related to specific programming commands or function calls

    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
     going
    -1.46
    Going
    -1.20
     Going
    -1.13
     GOING
    -1.12
     gonna
    -1.02
    going
    -0.98
     coming
    -0.89
     Gonna
    -0.89
    gonna
    -0.81
    coming
    -0.79
    POSITIVE LOGITS
    go
    2.78
    Go
    2.59
     Go
    2.56
     go
    2.48
    GO
    2.44
     GO
    2.36
    gos
    1.47
     gos
    1.20
    goe
    1.18
    ゴー
    1.17
    Activations Density 0.059%

    No Known Activations