© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 331
    Prev
    Next
    INDEX
    Explanations

    hyphens and characters surrounding them

    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
     ujednoznacz
    -0.64
     intptr
    -0.60
     للاسماء
    -0.57
     usta
    -0.56
     protoimpl
    -0.54
     "]";
    -0.52
    AlterField
    -0.50
     rischi
    -0.49
    "]));
    -0.48
     Legendre
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.68
    enumi
    0.63
    AsUp
    0.59
    subpackage
    0.59
     sẻ
    0.57
     esternos
    0.54
     Tabelle
    0.54
     onPostExecute
    0.52
    HIGHLIGHTS
    0.51
    asil
    0.50
    Activations Density 5.111%

    No Known Activations