© 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. 12129
    Prev
    Next
    INDEX
    Explanations

    nuisance

    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
     nuisance
    -0.98
     nuis
    -0.69
    ↵↵
    -0.45
     
    -0.43
     radio
    -0.41
    uis
    -0.41
     lend
    -0.41
     mind
    -0.38
     let
    -0.38
    <eos>
    -0.36
    POSITIVE LOGITS
    ThroughAttribute
    1.00
     pinulongan
    0.94
     متعلقه
    0.90
     AspNetCore
    0.82
     tartalomajánló
    0.82
     Roskov
    0.81
    Tikang
    0.80
     محفوظة
    0.80
    principalColumn
    0.79
    Sucesor
    0.79
    Activations Density 0.146%

    No Known Activations