© 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. 1-CLT-HP
    4. 12253
    Prev
    Next
    INDEX
    Explanations

    medicine and research

    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
    obic
    -2.02
     jScrollPane
    -0.47
    phens
    -0.43
    tedrale
    -0.42
     BrowserModule
    -0.41
     Sert
    -0.41
    rolled
    -0.40
    قایناق‌لار
    -0.40
     रही
    -0.40
    ob
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.90
     BoxFit
    0.69
     ComVisible
    0.65
     Cooking
    0.60
     CreateTagHelper
    0.60
    iddhar
    0.59
     ujednoznacz
    0.58
    EndInit
    0.57
     Edelman
    0.57
    IntoConstraints
    0.56
    Activations Density 0.009%

    No Known Activations