© 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. 3-RES-MATRYOSHKA-DC
    7. 1852
    Prev
    Next
    INDEX
    Explanations

    capitalized words and partial words within certain topics

    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
    Portale
    -0.90
    usermodel
    -0.80
     Bick
    -0.79
     desemple
    -0.78
     Berikut
    -0.76
    Aur
    -0.76
     Yud
    -0.76
     endothe
    -0.74
     méd
    -0.73
    Berikut
    -0.73
    POSITIVE LOGITS
    s
    2.25
    sted
    1.10
    ים
    0.94
    ی
    0.93
    ség
    0.91
    ات
    0.90
    ся
    0.89
    smith
    0.88
    sver
    0.88
    )");
    0.84
    Activations Density 6.950%

    No Known Activations