© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41847
    Prev
    Next
    INDEX
    Explanations

    none

    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
     purpoſe
    -1.08
     pleaſure
    -1.02
     cauſe
    -0.95
     Houſe
    -0.95
     Jefus
    -0.94
     myſelf
    -0.93
     uſe
    -0.90
     Diſ
    -0.90
     ſche
    -0.90
     Anſ
    -0.89
    POSITIVE LOGITS
     th
    0.63
    ChildScrollView
    0.57
    ValueStyle
    0.56
    ResponseWriter
    0.55
     or
    0.55
     Lav
    0.53
     RoutedEventArgs
    0.52
     den
    0.51
     sa
    0.49
     ver
    0.48
    Activations Density 0.333%

    No Known Activations