© 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. 45524
    Prev
    Next
    INDEX
    Explanations

    chemical and geographical

    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
    -0.92
    AddTagHelper
    -0.90
    contentLoaded
    -0.90
     myſelf
    -0.89
     itſelf
    -0.88
     Jefus
    -0.87
     pinulongan
    -0.83
     للاسماء
    -0.82
     reaſon
    -0.81
     pleaſure
    -0.80
    POSITIVE LOGITS
     over
    0.42
    <eos>
    0.41
     on
    0.39
     (=
    0.39
     one
    0.38
     (-
    0.38
    ரிய
    0.37
     fi
    0.36
     speed
    0.36
    tum
    0.36
    Activations Density 0.024%

    No Known Activations