© 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. 4-CLT-HP
    4. 3382
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     ujednoznacz
    -0.63
     препратки
    -0.63
     himo
    -0.62
    fjspx
    -0.61
     kaynağından
    -0.56
     beginnetje
    -0.54
    '}>
    -0.52
     للمعارف
    -0.52
    WriteTagHelper
    -0.48
    🇧
    -0.48
    POSITIVE LOGITS
    ísimas
    0.64
    twimg
    0.56
    portál
    0.55
    ParallelGroup
    0.54
     financières
    0.53
     nastro
    0.53
     hés
    0.52
     fær
    0.52
    GIH
    0.51
    OrCreate
    0.51
    Activations Density 0.001%

    No Known Activations