Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74522
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · 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
     '\\;'
    -0.84
    sizeCache
    -0.73
    getSystemService
    -0.64
    Personensuche
    -0.64
    Portale
    -0.62
    /*++
    -0.61
     <=",
    -0.61
    ᅠ
    -0.60
    بوابة
    -0.59
    stylers
    -0.58
    POSITIVE LOGITS
    +:+
    0.53
    ulite
    0.46
     Ruman
    0.45
     boleto
    0.44
     Ruß
    0.42
    labelControl
    0.42
     الحره
    0.41
     elettrica
    0.40
     GenerationType
    0.40
     laiton
    0.39
    Activations Density 0.005%

    No Known Activations