© 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. 5-CLT-HP
    4. 1137
    Prev
    Next
    INDEX
    Explanations

    en

    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
    رشف
    -0.69
    endphp
    -0.65
    ậy
    -0.55
     pull
    -0.54
     reck
    -0.52
     Pul
    -0.51
    hezza
    -0.50
     Hert
    -0.50
     Pull
    -0.49
    sizeCache
    -0.48
    POSITIVE LOGITS
    expandindo
    0.60
     avoient
    0.60
    queryInterface
    0.60
     banques
    0.60
     étoient
    0.60
     GenerationType
    0.58
    Chham
    0.58
    THISDAY
    0.57
    zzleHttp
    0.57
    Enllaces
    0.57
    Activations Density 0.002%

    No Known Activations