© 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. 12779
    Prev
    Next
    INDEX
    Explanations

    actions related to developing or creating

    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
     developing
    -0.97
     Developing
    -0.88
    developing
    -0.84
     emerging
    -0.74
    Developing
    -0.73
     evolving
    -0.64
     unborn
    -0.61
     fetus
    -0.59
     Emerging
    -0.57
     embryo
    -0.55
    POSITIVE LOGITS
     develop
    1.02
    develop
    0.88
     Develop
    0.82
     nakalista
    0.78
    Develop
    0.68
     BoxDecoration
    0.67
    DispatchToProps
    0.66
    yntaxException
    0.66
     develops
    0.63
    RepeatedField
    0.59
    Activations Density 0.004%

    No Known Activations