© 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. 2-RES-MATRYOSHKA-DC
    7. 3043
    Prev
    Next
    INDEX
    Explanations

    the decision to commit to a particular course of action

    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
    ----</
    -0.74
    selecting
    -0.73
    ypal
    -0.71
    مصادر
    -0.69
     selec
    -0.69
     елның
    -0.68
     selection
    -0.68
    URUS
    -0.68
     selections
    -0.67
    NameInMap
    -0.67
    POSITIVE LOGITS
     decided
    2.53
    decided
    2.19
     Decided
    2.19
     decide
    2.17
     decides
    2.17
     Decide
    1.88
    Decide
    1.80
    Decided
    1.78
    decide
    1.73
     deciding
    1.70
    Activations Density 0.037%

    No Known Activations