© 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. 0-CLT-HP
    7. 91018
    Prev
    Next
    INDEX
    Explanations

    native

    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
    native
    -1.56
     native
    -1.45
    Native
    -1.38
     Native
    -1.20
     nativo
    -1.09
    NATIVE
    -1.04
     nativa
    -0.98
     natives
    -0.97
    natives
    -0.91
     indigenous
    -0.88
    POSITIVE LOGITS
     '\\;'
    0.73
    AnchorStyles
    0.65
     catch
    0.60
    upol
    0.60
    bewerken
    0.59
     Maris
    0.59
    leman
    0.57
     Union
    0.57
    iolis
    0.56
     bird
    0.55
    Activations Density 0.100%

    No Known Activations