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. 1-CLT-HP
    4. 12800
    Prev
    Next
    INDEX
    Explanations

    fonts

    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
     gynhyrchwyd
    -0.94
     propOrder
    -0.83
     GenerationType
    -0.78
     }}-
    -0.72
     <",
    -0.71
    Atsauces
    -0.69
     Meksiku
    -0.69
     AppCompatTheme
    -0.69
     <=",
    -0.69
     })
    
    -0.68
    POSITIVE LOGITS
     or
    0.48
    ,
    0.43
    thio
    0.42
    igslist
    0.41
     hectáreas
    0.41
     has
    0.40
     
    0.40
    BrowserModule
    0.40
    hpur
    0.39
    telegraph
    0.38
    Activations Density 0.180%

    No Known Activations