© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    moments of immediate action or response

    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
    SharedDtor
    -1.10
    RegressionTest
    -1.03
    WireFormatLite
    -0.91
    fjspx
    -0.90
     doInBackground
    -0.84
     الحره
    -0.84
    Rapid
    -0.82
    Slowly
    -0.82
    KURZBESCHREIBUNG
    -0.82
    slowly
    -0.81
    POSITIVE LOGITS
     immediately
    2.64
     immediate
    2.48
    immediately
    2.34
     Immediately
    2.31
    Immediate
    2.28
    Immediately
    2.23
     Immediate
    2.22
    immediate
    2.17
     immédiatement
    2.06
     IMMEDIATE
    1.97
    Activations Density 0.009%

    No Known Activations