© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73697
    Prev
    Next
    INDEX
    Explanations

    log

    np_max-act-logits · 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
     ujednoznacz
    -0.63
    RUnlock
    -0.63
     مشين
    -0.57
     useState
    -0.56
    rungsseite
    -0.54
    الحياه
    -0.52
    MLLoader
    -0.52
    ScopeManager
    -0.52
    তথ্যসূত্র
    -0.52
    sikal
    -0.51
    POSITIVE LOGITS
    ParallelGroup
    0.59
    on
    0.58
    tagHelper
    0.56
     on
    0.50
    On
    0.49
    オン
    0.49
    onSearch
    0.46
    Hentet
    0.45
    ̀i
    0.45
    odds
    0.45
    Activations Density 0.002%

    No Known Activations