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. 0-CLT-HP
    4. 945
    Prev
    Next
    INDEX
    Explanations

    online snippets

    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
    Personendaten
    -1.01
     betweenstory
    -0.96
     itſelf
    -0.89
    :+:
    -0.88
    MessageOf
    -0.88
    ArgsConstructor
    -0.84
    UnusedPrivate
    -0.84
     AssemblyProduct
    -0.79
     Roskov
    -0.77
    GEBURTSDATUM
    -0.77
    POSITIVE LOGITS
     The
    0.57
     and
    0.54
     
    0.54
     In
    0.53
     in
    0.51
     H
    0.50
     Human
    0.49
     A
    0.49
     E
    0.48
     [
    0.47
    Activations Density 1.760%

    No Known Activations