© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43599
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Personendaten
    -0.67
    onViewCreated
    -0.66
     localObject
    -0.66
     vPvB
    -0.65
     CreateTagHelper
    -0.63
    دانشنامهٔ
    -0.63
    ustimmung
    -0.61
     Италијани
    -0.60
     swarms
    -0.59
    ########.
    -0.59
    POSITIVE LOGITS
     بتاريخ
    0.55
    LookAnd
    0.54
    ্ত
    0.49
    зной
    0.46
     wish
    0.46
    setGravity
    0.45
    baomidou
    0.44
    Estat
    0.44
     })}
    0.43
    faker
    0.42
    Activations Density 0.056%

    No Known Activations