© 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. 20-CLT-HP
    7. 74651
    Prev
    Next
    INDEX
    Explanations

    biological processes

    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
     Wikimédia
    -0.66
     purpoſe
    -0.65
    Према
    -0.64
     vägen
    -0.63
     nakalista
    -0.62
    ledo
    -0.60
    viewDidLoad
    -0.60
     ſche
    -0.59
     differentiation
    -0.59
    ябре
    -0.59
    POSITIVE LOGITS
     Audiodateien
    0.57
     مشين
    0.52
    ScopeManager
    0.52
     broken
    0.50
    DotNetBar
    0.43
    FXMLLoader
    0.43
     fun
    0.41
     ktorí
    0.41
     used
    0.40
     repro
    0.40
    Activations Density 0.002%

    No Known Activations