© 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. 4-CLT-HP
    7. 4586
    Prev
    Next
    INDEX
    Explanations

    Expressing desires or thoughts

    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
    ImageContext
    -0.68
    AddTagHelper
    -0.66
    ScopeManager
    -0.66
    __':
    -0.64
    ViewFeatures
    -0.63
    Välislingid
    -0.63
     ExecuteAsync
    -0.61
    TagMode
    -0.60
     bağlantılar
    -0.59
     Acerca
    -0.59
    POSITIVE LOGITS
    RegistryLite
    0.49
     làn
    0.47
     FixedUpdate
    0.45
    baijan
    0.45
    Hozzáférés
    0.45
     organisers
    0.45
    llion
    0.44
    至此
    0.44
     Organisation
    0.44
     Zor
    0.44
    Activations Density 0.001%

    No Known Activations