© 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. 2967
    Prev
    Next
    INDEX
    Explanations

    decimal numbers within mathematical or academic writing

    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
    veira
    -0.50
    UVWXYZ
    -0.50
     <>",
    -0.49
    JsonKey
    -0.49
    lename
    -0.47
     helst
    -0.47
     calculées
    -0.46
    fycat
    -0.46
    Scaler
    -0.45
    ValueStyle
    -0.45
    POSITIVE LOGITS
    subsubsection
    0.66
    المناصب
    0.63
    subsection
    0.63
    >--}}
    0.62
    NUMX
    0.61
     concreto
    0.58
    脚注の使い方
    0.57
     concret
    0.57
    :{}
    0.57
     sapon
    0.56
    Activations Density 0.373%

    No Known Activations