© 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. 11922
    Prev
    Next
    INDEX
    Explanations

    proper names or references

    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
     виправивши
    -0.75
     purpoſe
    -0.66
    glGen
    -0.60
     ſeveral
    -0.59
     Reſ
    -0.59
     divertimento
    -0.59
     cauſe
    -0.59
     Diri
    -0.59
     anhydrous
    -0.59
     houſe
    -0.59
    POSITIVE LOGITS
     Kas
    3.20
    Kas
    2.97
     kas
    2.36
    kas
    1.77
     KAS
    1.59
    KAS
    1.48
     Kass
    0.83
     Kasper
    0.69
     يتيمه
    0.68
     MainAxisSize
    0.64
    Activations Density 0.000%

    No Known Activations