© 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. 1-CLT-HP
    7. 13345
    Prev
    Next
    INDEX
    Explanations

    group

    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
    tvguidetime
    -0.71
     brancas
    -0.55
     engraçadas
    -0.54
    */),
    -0.53
     perlahan
    -0.52
     définiti
    -0.52
     segi
    -0.51
     vermelhas
    -0.51
     kautta
    -0.49
     avulla
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.65
     pherom
    0.63
    ็จ
    0.63
     bathed
    0.59
     feathers
    0.57
    AutoScaleMode
    0.55
     potatoes
    0.54
     locust
    0.54
     pyrite
    0.54
     defraud
    0.51
    Activations Density 0.007%

    No Known Activations