© 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. 5-CLT-HP
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    preference/favor

    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
    SerializedSize
    -0.60
     /\.
    -0.56
     Congrats
    -0.54
     brava
    -0.52
    ponential
    -0.52
    MinWidth
    -0.51
    rews
    -0.51
    grès
    -0.50
    ]));
    -0.50
    NameInMap
    -0.50
    POSITIVE LOGITS
     parlent
    0.56
     receber
    0.50
     tett
    0.48
    uncle
    0.48
     touristes
    0.47
    tine
    0.47
    AndEndTag
    0.46
     AssemblyTitle
    0.46
     atender
    0.46
    Treatment
    0.45
    Activations Density 0.002%

    No Known Activations