© 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. 5-CLT-HP
    7. 95113
    Prev
    Next
    INDEX
    Explanations

    of

    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
    setVerticalGroup
    -0.61
     onBind
    -0.57
    ItemBackground
    -0.53
    viewDidLoad
    -0.52
    urtstag
    -0.50
    cipais
    -0.46
     mol
    -0.45
    MessageOf
    -0.43
    ũng
    -0.43
     AssemblyCulture
    -0.43
    POSITIVE LOGITS
     дописавши
    0.65
     case
    0.55
     pressione
    0.54
    AndEndTag
    0.54
    Билгалдахарш
    0.54
    oa̍t
    0.52
     pensées
    0.52
     tendenza
    0.52
    SequentialGroup
    0.52
    QUESTIONS
    0.52
    Activations Density 0.004%

    No Known Activations