© 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. 20-CLT-HP
    7. 74842
    Prev
    Next
    INDEX
    Explanations

    Code-related identifiers

    np_max-act-logits · 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
     &___
    -0.43
     متعلقه
    -0.42
     noten
    -0.39
     g
    -0.39
    وده
    -0.37
    Target
    -0.37
    Campos
    -0.37
     supo
    -0.37
     گو
    -0.36
     vio
    -0.35
    POSITIVE LOGITS
    </tfoot>
    0.75
     <<<<<<<<<<<<<<
    0.72
     pleaſure
    0.70
    UIControlState
    0.66
    mphs
    0.65
    reportWebVitals
    0.65
    енча
    0.63
    FunctionFlags
    0.63
     فريبيس
    0.63
     htons
    0.61
    Activations Density 0.000%

    No Known Activations