© 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. 4-CLT-HP
    7. 4846
    Prev
    Next
    INDEX
    Explanations

    Og

    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
    PreferredItem
    -0.54
     <=",
    -0.50
    RegressionTest
    -0.49
    PropertyChanging
    -0.47
    oar
    -0.44
    ➟
    -0.44
     ra
    -0.43
     jspb
    -0.42
    argento
    -0.41
    twimg
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.66
     fufficient
    0.61
     contextLoads
    0.59
    SequentialGroup
    0.59
    脚注の使い方
    0.57
    Monument
    0.56
     esternos
    0.56
     Pani
    0.56
     stockings
    0.55
     ſtill
    0.54
    Activations Density 0.010%

    No Known Activations