© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 11777
    Prev
    Next
    INDEX
    Explanations

    references to specific keywords or phrases related to family history, especially involving the word "tw" (likely indicating "twin" or "two") and the cemetery name "Rocky Springs Cemetery", suggesting it is focused on identifying mentions of familial or ancestral locations and related details

    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
    TYPED
    -0.57
     onder
    -0.56
    Бахар
    -0.55
     vne
    -0.55
     poda
    -0.53
    ród
    -0.53
     Himo
    -0.52
     conos
    -0.52
    بوابة
    -0.51
     Leit
    -0.51
    POSITIVE LOGITS
     дописавши
    0.89
     tw
    0.81
     tre
    0.76
     thi
    0.70
     Leeuwen
    0.69
     noDo
    0.69
    الحياه
    0.69
    verif
    0.68
     swine
    0.68
    superuser
    0.65
    Activations Density 0.079%

    No Known Activations