© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92625
    Prev
    Next
    INDEX
    Explanations

    rejuven

    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
    िन्न
    -0.46
     autor
    -0.44
    skapet
    -0.43
    lampen
    -0.41
     ir
    -0.41
    addWidget
    -0.41
    lades
    -0.41
    liminary
    -0.40
    keiten
    -0.40
    Chúng
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.88
    ed
    0.85
     ModelExpression
    0.82
     himo
    0.79
     Houſe
    0.79
     uſed
    0.78
     Monfieur
    0.76
    ContentAlignment
    0.75
    脚注の使い方
    0.75
     uſe
    0.75
    Activations Density 0.167%

    No Known Activations