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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5881
    Prev
    Next
    INDEX
    Explanations

    transcription

    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
     CreateTagHelper
    -0.88
    parsedMessage
    -0.68
    󠁿
    -0.66
    anship
    -0.66
    
    -0.64
    uxxxx
    -0.61
     initComponents
    -0.61
    AndEndTag
    -0.60
    出版年
    -0.60
     resourceCulture
    -0.58
    POSITIVE LOGITS
     islas
    0.44
    Sucesor
    0.43
     épreuves
    0.43
    مراجع
    0.42
     vPvB
    0.42
     esperienze
    0.41
    :+:
    0.41
     通販
    0.40
    ,
    0.39
     liitty
    0.39
    Activations Density 0.003%

    No Known Activations