© 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. 2104
    Prev
    Next
    INDEX
    Explanations

    Introductions

    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
     defaultstate
    -0.66
    +};
    -0.62
     Мексичка
    -0.60
     ddelweddau
    -0.59
     autorytatywna
    -0.59
     Waray
    -0.58
    》.
    -0.58
     censiti
    -0.56
    OrFail
    -0.56
    modelBuilder
    -0.55
    POSITIVE LOGITS
     BoxDecoration
    0.52
     now
    0.52
    #+#
    0.49
    LEncoder
    0.47
     Celui
    0.46
     excuse
    0.46
    ยว
    0.45
     دریافت‌شده
    0.44
     artık
    0.44
    hmig
    0.42
    Activations Density 0.017%

    No Known Activations