© 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. 0-RES-MATRYOSHKA-DC
    7. 12330
    Prev
    Next
    INDEX
    Explanations

    references to the collective group or community

    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
    our
    -1.23
    OUR
    -1.21
    ours
    -0.98
     Our
    -0.94
    Our
    -0.89
    OURS
    -0.84
    Ours
    -0.78
     Ours
    -0.75
    ouring
    -0.74
    she
    -0.70
    POSITIVE LOGITS
     Efq
    0.68
    endforeach
    0.65
    RectangleBorder
    0.63
    stalgia
    0.61
    didSet
    0.59
     Paglinawan
    0.59
    नलिखित
    0.59
     combineReducers
    0.58
    ensement
    0.57
    issex
    0.57
    Activations Density 0.046%

    No Known Activations