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. 20-CLT-HP
    4. 74086
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     at
    -0.78
    },{
    
    -0.51
    serialization
    -0.50
     Wob
    -0.50
    ANNES
    -0.49
    Datuak
    -0.49
     Weis
    -0.48
    სქოლიო
    -0.48
    At
    -0.48
    loyment
    -0.47
    POSITIVE LOGITS
     дописавши
    0.66
     beginnetje
    0.56
     tartalomajánló
    0.53
    (!__
    0.51
    hassee
    0.51
    AsUp
    0.49
     overtime
    0.46
     FetchType
    0.46
     compensated
    0.46
    enderror
    0.46
    Activations Density 0.001%

    No Known Activations