© 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. 158
    Prev
    Next
    INDEX
    Explanations

    the string "pone" which appears to be part of a citation

    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
    Endian
    -0.57
    ություն
    -0.56
     notori
    -0.56
    是多少
    -0.55
     match
    -0.55
     Boas
    -0.54
    bewah
    -0.54
     Canaria
    -0.52
    niana
    -0.52
    ナメント
    -0.52
    POSITIVE LOGITS
    pone
    3.05
    PONE
    1.70
     pone
    1.33
    bootstrapcdn
    1.18
     مشين
    0.92
    pon
    0.91
    openzeppelin
    0.84
     EEU
    0.81
    PON
    0.79
    ⓧ
    0.74
    Activations Density 0.206%

    No Known Activations