© 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. 98005
    Prev
    Next
    INDEX
    Explanations

    zero

    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
     "%"
    -0.47
    alek
    -0.46
    しか
    -0.42
    WriteTagHelper
    -0.41
    labelledby
    -0.41
     weakness
    -0.40
     Kish
    -0.40
     '%'
    -0.40
     MongoClient
    -0.40
     sufferer
    -0.40
    POSITIVE LOGITS
    клопе
    0.64
    ніципа
    0.62
    ametro
    0.61
    setVerticalGroup
    0.61
    BeginInit
    0.60
     acadé
    0.59
    RefNanny
    0.59
     traffico
    0.57
    ελ
    0.57
    0
    0.57
    Activations Density 0.025%

    No Known Activations