© 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. 0-CLT-HP
    7. 40078
    Prev
    Next
    INDEX
    Explanations

    causative

    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
     religieuse
    -0.72
     chinoise
    -0.70
     abstrait
    -0.70
     vectorielle
    -0.69
     japonaise
    -0.69
     grecque
    -0.67
    styleType
    -0.66
     gratuites
    -0.65
     heureuse
    -0.65
     médicale
    -0.65
    POSITIVE LOGITS
    y
    0.60
    s
    0.57
    tifies
    0.57
    d
    0.55
    er
    0.54
    sticks
    0.54
    en
    0.52
    a
    0.49
    ering
    0.49
    aly
    0.48
    Activations Density 0.144%

    No Known Activations