© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45852
    Prev
    Next
    INDEX
    Explanations

    sports and training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.46
     sebesar
    -0.45
    getBean
    -0.45
    breviation
    -0.44
    training
    -0.44
    trainer
    -0.44
    FormTagHelper
    -0.43
     puissiez
    -0.43
     hom
    -0.43
     doInBackground
    -0.42
    POSITIVE LOGITS
     Diſ
    0.66
    EndInit
    0.66
    出版年
    0.65
     houſe
    0.63
     snippetHide
    0.63
    :✨
    0.61
     Houſe
    0.60
    ()?;
    0.59
     Theſe
    0.58
     Reſ
    0.57
    Activations Density 0.061%

    No Known Activations