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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96076
    Prev
    Next
    INDEX
    Explanations

    religion

    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
    SourceChecksum
    -0.84
    <bos>
    -0.78
    Portale
    -0.77
     الرياضيه
    -0.75
     архивлан
    -0.75
     CreateTagHelper
    -0.74
    脚注の使い方
    -0.73
     Paglinawan
    -0.73
    SequentialGroup
    -0.72
    ंदीखरीदारी
    -0.70
    POSITIVE LOGITS
     väli
    0.47
     Helena
    0.44
     Seychelles
    0.44
     strijd
    0.43
     auttaa
    0.43
     aantal
    0.43
     näky
    0.43
     aikaa
    0.42
     Gilles
    0.41
     työn
    0.41
    Activations Density 0.005%

    No Known Activations