Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 208
    Prev
    Next
    INDEX
    Explanations

    {{

    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
     AssemblyCulture
    -0.56
     nonatomic
    -0.56
    GEBURTSDATUM
    -0.55
    Composable
    -0.54
     InputDecoration
    -0.54
    NameInMap
    -0.54
    AndEndTag
    -0.54
     connues
    -0.53
    ReusableCell
    -0.52
     preuves
    -0.52
    POSITIVE LOGITS
    참고
    0.57
    chial
    0.54
    Хьажоргаш
    0.54
    itures
    0.53
     Мексичка
    0.52
     disad
    0.52
     amended
    0.51
    Amended
    0.51
    itra
    0.50
     Bourgoin
    0.49
    Activations Density 0.840%

    No Known Activations