© 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. 0-CLT-HP
    7. 43649
    Prev
    Next
    INDEX
    Explanations

    immun

    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
     trigger
    -0.65
     Trigger
    -0.51
     pet
    -0.49
    Trigger
    -0.49
    trigger
    -0.49
     antigen
    -0.46
     vent
    -0.45
     net
    -0.45
     quantum
    -0.44
     Newton
    -0.43
    POSITIVE LOGITS
    下载附件
    0.89
    tiness
    0.84
    itarianism
    0.75
    存于互联网档案馆
    0.73
    Искәрмәләр
    0.70
     Normdatei
    0.69
    DoubleQuotes
    0.69
    izability
    0.69
    itarian
    0.68
    isable
    0.68
    Activations Density 0.335%

    No Known Activations