© 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. 6-RES-MATRYOSHKA-DC
    7. 273
    Prev
    Next
    INDEX
    Explanations

    instances of choosing or rejecting

    oai_token-act-pair · gemini-2.0-flash
    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
    ViewFeatures
    -0.88
    ecake
    -0.73
     adanya
    -0.69
    ocumented
    -0.68
     nyata
    -0.68
    pielt
    -0.65
     bezeichneter
    -0.65
    лаго
    -0.63
     grpc
    -0.62
    deed
    -0.62
    POSITIVE LOGITS
     choice
    1.93
     choosing
    1.84
     selects
    1.83
     choose
    1.82
     Choosing
    1.79
     selection
    1.77
     chooses
    1.76
     Selection
    1.74
     Choice
    1.73
     chosen
    1.73
    Activations Density 2.078%

    No Known Activations