© 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. 1-CLT-HP
    7. 45875
    Prev
    Next
    INDEX
    Explanations

    titles

    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
    ⓧ
    -0.68
     Roskov
    -0.63
     ultimatum
    -0.53
     guarded
    -0.52
    elemField
    -0.52
     loch
    -0.50
     eradicated
    -0.50
    eaux
    -0.50
    ंदीखरीदारी
    -0.50
    +#+#
    -0.50
    POSITIVE LOGITS
     समीक्षक
    0.57
    execSQL
    0.54
    AxisAlignment
    0.51
    DataMember
    0.48
     sintético
    0.48
    MemoryWarning
    0.47
    ClientSize
    0.47
    ọi
    0.47
    ngine
    0.45
    CopyWith
    0.45
    Activations Density 0.040%

    No Known Activations