© 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. 38691
    Prev
    Next
    INDEX
    Explanations

    mythology and folklore

    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
     Efq
    -0.89
     légende
    -0.85
     feroit
    -0.82
     Jefus
    -0.81
     auroit
    -0.80
     ſtate
    -0.79
     houſe
    -0.79
     legend
    -0.77
    esterday
    -0.75
     Houſe
    -0.75
    POSITIVE LOGITS
    s
    0.97
    less
    0.70
    hips
    0.69
    z
    0.68
    ing
    0.67
    ,
    0.65
    ry
    0.63
    n
    0.63
    san
    0.61
    la
    0.60
    Activations Density 0.502%

    No Known Activations