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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94679
    Prev
    Next
    INDEX
    Explanations

    tasks, roles, functions

    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
    awtextra
    -0.77
     EconPapers
    -0.64
    endphp
    -0.56
     <=",
    -0.55
     <>",
    -0.53
    StoryboardSegue
    -0.49
    TemporalType
    -0.49
     برانيه
    -0.48
    rawDesc
    -0.47
     الرخصة
    -0.46
    POSITIVE LOGITS
     for
    0.76
     critical
    0.65
     Wiktionnaire
    0.64
     that
    0.58
     essential
    0.56
    enterOuterAlt
    0.55
     in
    0.53
     necessary
    0.53
    principalTable
    0.52
    łoży
    0.52
    Activations Density 0.003%

    No Known Activations