© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13220
    Prev
    Next
    INDEX
    Explanations

    chip

    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
     Trit
    -0.47
     lumens
    -0.46
    fastjson
    -0.46
    andExpect
    -0.45
    jsonwebtoken
    -0.45
     <<<<<<<<<<<<<<
    -0.44
    Свет
    -0.44
    بسم
    -0.43
    FileDescriptor
    -0.43
    وفاته
    -0.43
    POSITIVE LOGITS
    findpost
    0.66
     BoxFit
    0.63
    Expedia
    0.60
     désolés
    0.59
    port
    0.59
    front
    0.59
    IUrlHelper
    0.58
     ostavi
    0.57
    portar
    0.57
    GEBURTSDATUM
    0.57
    Activations Density 0.014%

    No Known Activations