© 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. 74563
    Prev
    Next
    INDEX
    Explanations

    Code 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
    gway
    -0.59
     ]]
    -0.53
     tslint
    -0.52
     indisponible
    -0.51
    ParallelGroup
    -0.48
    expandindo
    -0.48
     crave
    -0.47
    Portail
    -0.47
    OrWhiteSpace
    -0.47
    orphic
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.88
     فريبيس
    0.56
    évaluateur
    0.56
    ngrx
    0.54
    Aktualisiert
    0.53
     estekak
    0.52
     éclair
    0.52
    SqlSession
    0.51
    аз
    0.49
    UpInside
    0.48
    Activations Density 0.001%

    No Known Activations