© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    with

    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
     solidarité
    -0.67
    ご注意
    -0.60
     giusti
    -0.60
    DoubleQuotes
    -0.59
     riktig
    -0.57
     veille
    -0.57
    Beware
    -0.57
    才行
    -0.56
    Sucesor
    -0.56
     Beware
    -0.55
    POSITIVE LOGITS
    fromnode
    0.63
    LookAnd
    0.61
     autorytatywna
    0.57
     onBind
    0.55
    lepiej
    0.52
    execSQL
    0.50
    domada
    0.49
    '){
    0.48
    ंदीखरीदारी
    0.48
    ➟
    0.48
    Activations Density 0.025%

    No Known Activations