© 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. 4-CLT-HP
    7. 4915
    Prev
    Next
    INDEX
    Explanations

    detailed

    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
     avoient
    -0.98
     enfans
    -0.95
     blessés
    -0.88
    WriteTagHelper
    -0.85
     soigneusement
    -0.85
     malheureux
    -0.85
     quelcon
    -0.82
     coû
    -0.82
     puissante
    -0.82
     étoient
    -0.82
    POSITIVE LOGITS
     new
    0.59
     —
    0.47
     -
    0.44
     mental
    0.42
     –
    0.41
    new
    0.41
     mắn
    0.40
    ochet
    0.39
    —
    0.38
     psychological
    0.38
    Activations Density 0.001%

    No Known Activations