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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74508
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act-logits · 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
    Slf
    -0.63
    utilisons
    -0.60
    AndEndTag
    -0.58
    yelitis
    -0.57
    setVerticalGroup
    -0.55
     برانيه
    -0.55
     FetchType
    -0.53
     <>",
    -0.53
    TestTools
    -0.52
    ggars
    -0.51
    POSITIVE LOGITS
    law
    0.54
    Hå
    0.50
    énario
    0.50
    contentLoaded
    0.50
    Reprints
    0.50
    }],
    
    0.49
     Lawler
    0.49
     law
    0.48
    +#+
    0.47
     عرب
    0.47
    Activations Density 0.000%

    No Known Activations