© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92463
    Prev
    Next
    INDEX
    Explanations

    reputation and stories

    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
     prejudice
    -0.82
     rocket
    -0.75
     myth
    -0.73
    esteem
    -0.72
     esteem
    -0.70
     superstition
    -0.68
     stereotypes
    -0.68
     Etiquette
    -0.66
    ={`/
    -0.65
    ]='\
    -0.65
    POSITIVE LOGITS
     suit
    0.61
    SequentialGroup
    0.54
    suit
    0.53
    <bos>
    0.51
     and
    0.51
    ly
    0.50
     nahilalakip
    0.50
    styleType
    0.49
    ess
    0.48
    the
    0.48
    Activations Density 0.434%

    No Known Activations