© 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. 854
    Prev
    Next
    INDEX
    Explanations

    pages

    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
    Pages
    -1.08
    hagen
    -0.77
    Artem
    -0.52
     beginnetje
    -0.49
     Artem
    -0.44
     Erişim
    -0.43
     متحده
    -0.42
     Expédié
    -0.42
     poveznice
    -0.41
     intptr
    -0.40
    POSITIVE LOGITS
     ioutil
    0.56
     ujednoznacz
    0.55
    습니다
    0.53
    withstanding
    0.53
    ListItemIcon
    0.52
    antiation
    0.52
     popula
    0.51
     stripper
    0.51
    ities
    0.51
    ToScroll
    0.51
    Activations Density 0.014%

    No Known Activations