© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45323
    Prev
    Next
    INDEX
    Explanations

    Dolphins

    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
    ue
    -0.73
    UE
    -0.66
     
    -0.63
    ing
    -0.60
    ING
    -0.56
      
    -0.51
    ume
    -0.50
    UME
    -0.50
    umen
    -0.47
     P
    -0.47
    POSITIVE LOGITS
     Roskov
    1.50
    +#+#
    1.43
     Мексичка
    1.36
    verwijspagina
    1.32
    aarrggbb
    1.30
     AssemblyCulture
    1.28
    expandindo
    1.28
    GEBURTSDATUM
    1.28
     дописавши
    1.25
    tagHelperRunner
    1.24
    Activations Density 0.089%

    No Known Activations