© 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. 20-CLT-HP
    7. 74696
    Prev
    Next
    INDEX
    Explanations

    Uncommon words or text snippets

    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
     ARS
    -0.54
    cektir
    -0.53
     فريبيس
    -0.53
    IVAS
    -0.52
     يتيمه
    -0.50
    ząt
    -0.50
    marshaller
    -0.50
    iru
    -0.50
     []).
    -0.50
     Asha
    -0.49
    POSITIVE LOGITS
    sedown
    0.53
     Schicht
    0.52
    CodeDom
    0.49
    Geplaatst
    0.48
     kaynağından
    0.46
    ubel
    0.46
    oa̍t
    0.45
    epiece
    0.44
     viewDidLoad
    0.44
    Билгалдахарш
    0.44
    Activations Density 0.002%

    No Known Activations