© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    references to substituting or replacing components

    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
    IntoConstraints
    -0.78
     مرئيه
    -0.66
    NewGuid
    -0.65
    []
    -0.60
    Claro
    -0.59
     sharps
    -0.59
    andowski
    -0.56
    ument
    -0.55
    XtraGrid
    -0.55
     دیکھیے
    -0.55
    POSITIVE LOGITS
     Becker
    0.76
    fla
    0.73
     cing
    0.68
    terna
    0.63
    enberg
    0.63
    rsc
    0.63
    ower
    0.63
    onload
    0.62
    osity
    0.61
     motorists
    0.61
    Activations Density 0.066%

    No Known Activations