© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74671
    Prev
    Next
    INDEX
    Explanations

    scientific and technical texts

    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
    पया
    -0.69
     >=",
    -0.68
     تضيفلها
    -0.68
     виправивши
    -0.67
    IndentedString
    -0.64
    AddHtmlAttribute
    -0.61
    WebMethod
    -0.56
    Tazama
    -0.56
    LookAnd
    -0.56
    tagHelperRunner
    -0.56
    POSITIVE LOGITS
    issing
    0.53
    ọc
    0.53
    
    0.51
     termica
    0.49
    BRL
    0.45
     dévelo
    0.44
    httphttps
    0.44
    ISS
    0.43
     Chronicle
    0.43
    govia
    0.43
    Activations Density 0.002%

    No Known Activations