© 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. 0-CLT-HP
    7. 1147
    Prev
    Next
    INDEX
    Explanations

    {

    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
    NewUrlParser
    -0.60
    mybatisplus
    -0.55
    XmlIgnore
    -0.54
     transfieras
    -0.53
    Activités
    -0.52
    parsedMessage
    -0.50
    LookAnd
    -0.47
    GetLength
    -0.47
     Acc
    -0.46
    تص
    -0.45
    POSITIVE LOGITS
     <>",
    0.76
     الحره
    0.63
     thither
    0.63
     Hano
    0.60
     enää
    0.60
     picioare
    0.59
     raccol
    0.58
    inerja
    0.57
     cleansed
    0.57
     intptr
    0.57
    Activations Density 1.129%

    No Known Activations