© 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. 6-RES-MATRYOSHKA-DC
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    the word "version" and related words

    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
     InputDecoration
    -0.85
     propOrder
    -0.78
    ControllerAdvice
    -0.77
     odkazy
    -0.76
    makeConstraints
    -0.72
     חיצוניים
    -0.70
    IntoConstraints
    -0.70
    DEFINE
    -0.69
    المناصب
    -0.67
    itespace
    -0.66
    POSITIVE LOGITS
     version
    2.33
     versions
    2.33
     Version
    2.30
     VERSION
    2.20
    Version
    2.17
    version
    2.13
     Versions
    2.05
    VERSION
    1.89
    versions
    1.80
    Versions
    1.77
    Activations Density 0.562%

    No Known Activations