© 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. 1204
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    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
     ecco
    -0.66
    setVerticalGroup
    -0.64
     respectively
    -0.64
     instead
    -0.60
     either
    -0.60
     Bourgoin
    -0.59
     alternatively
    -0.58
     Either
    -0.57
     himmel
    -0.57
     voilà
    -0.55
    POSITIVE LOGITS
     Meksiku
    0.61
    Initializable
    0.59
     betweenstory
    0.59
     GenerationType
    0.58
    Begriffsklä
    0.56
     للمعارف
    0.49
     resourceCulture
    0.48
     ujednoznacz
    0.45
     '\\;'
    0.45
     AssemblyVersion
    0.45
    Activations Density 0.014%

    No Known Activations