© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4967
    Prev
    Next
    INDEX
    Explanations

    Immunosuppressant

    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
     الحره
    -0.49
     bağlı
    -0.49
     تانيه
    -0.47
    Hozzáférés
    -0.47
    osoba
    -0.44
     Baillargeon
    -0.43
    dota
    -0.43
    ้าง
    -0.42
     hilos
    -0.42
    IRD
    -0.41
    POSITIVE LOGITS
     صوتيه
    0.69
     autorytatywna
    0.62
     Steff
    0.60
    upassen
    0.55
    enumi
    0.55
     Roskov
    0.53
    gatsby
    0.52
     Ste
    0.52
    ayu
    0.52
    发表于
    0.51
    Activations Density 0.005%

    No Known Activations