© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41957
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
     hope
    -1.11
     hopes
    -0.80
     pride
    -0.67
    espoir
    -0.63
    ConstraintMaker
    -0.61
     joy
    -0.60
    theless
    -0.59
    anskje
    -0.59
     hoppas
    -0.59
     speranza
    -0.58
    POSITIVE LOGITS
    fulness
    0.77
    fully
    0.64
    Personendaten
    0.63
    URLException
    0.63
    ⓧ
    0.57
    ously
    0.57
    printStackTrace
    0.56
     kaarangay
    0.56
     VizieR
    0.56
    éndolo
    0.56
    Activations Density 0.054%

    No Known Activations