© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40655
    Prev
    Next
    INDEX
    Explanations

    debit

    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
    oredCriteria
    -1.06
    writeFieldEnd
    -1.01
    IsContent
    -0.98
     autorytatywna
    -0.98
    featureID
    -0.98
    Personensuche
    -0.95
    WebVitals
    -0.94
     itſelf
    -0.93
    parsedMessage
    -0.93
    Vidite
    -0.91
    POSITIVE LOGITS
     T
    0.49
    ding
    0.47
     V
    0.46
     Me
    0.44
     E
    0.44
     e
    0.44
     P
    0.43
     Lin
    0.43
     Min
    0.43
     B
    0.42
    Activations Density 0.142%

    No Known Activations