Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12570
    Prev
    Next
    INDEX
    Explanations

    muscle

    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
     }}}{
    -0.56
     genoux
    -0.54
     vervol
    -0.54
     épaules
    -0.53
     détru
    -0.52
    kaŭ
    -0.52
     varandra
    -0.52
     }}$}
    -0.51
     δὲ
    -0.51
     récompense
    -0.51
    POSITIVE LOGITS
     Express
    0.56
    InitVars
    0.56
    <bos>
    0.53
    WithIOException
    0.53
    Express
    0.51
    estacks
    0.50
     EconPapers
    0.47
    Dış
    0.47
     "..\..\
    0.47
     xen
    0.47
    Activations Density 0.032%

    No Known Activations