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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1308
    Prev
    Next
    INDEX
    Explanations

    finish

    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
     يتيمه
    -0.96
    GEBURTSDATUM
    -0.92
     مشين
    -0.75
     ddelweddau
    -0.72
    GenerationType
    -0.71
    protoimpl
    -0.69
    LookAnd
    -0.68
     saites
    -0.67
    MigrationBuilder
    -0.67
    Datuak
    -0.65
    POSITIVE LOGITS
     whatever
    0.63
     using
    0.60
     what
    0.56
     eating
    0.52
     with
    0.52
     speaking
    0.50
    using
    0.47
     hva
    0.47
     engaging
    0.45
     dig
    0.44
    Activations Density 0.001%

    No Known Activations