© 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. 1-CLT-HP
    7. 45579
    Prev
    Next
    INDEX
    Explanations

    fleet

    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
    <bos>
    -0.77
    $_['
    -0.67
    fromnode
    -0.59
    
    -0.58
    PRNewswire
    -0.57
     typelib
    -0.57
    expandindo
    -0.57
    ^(@)
    -0.56
     Paglinawan
    -0.56
    }:${
    -0.53
    POSITIVE LOGITS
    FieldBuilder
    0.63
    SpringRunner
    0.57
    ्यालय
    0.54
     
    0.54
    BeginContext
    0.52
    loyer
    0.52
     constexpr
    0.51
    isPresent
    0.51
    DebuggerNonUser
    0.49
    mentaux
    0.48
    Activations Density 4.098%

    No Known Activations