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. 20-CLT-HP
    4. 74110
    Prev
    Next
    INDEX
    Explanations

    code and technical

    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
     تضيفلها
    -0.70
    FieldOffset
    -0.59
     pinulongan
    -0.52
    ardin
    -0.50
    TagHelper
    -0.50
     Daß
    -0.50
    Tia
    -0.49
     VizieR
    -0.49
     Open
    -0.49
    AddRef
    -0.49
    POSITIVE LOGITS
    verwijspagina
    0.61
     rent
    0.56
     hop
    0.53
     get
    0.52
    fjspx
    0.51
    
    0.50
    IsMutable
    0.50
     RENT
    0.49
    SequentialGroup
    0.48
    get
    0.47
    Activations Density 0.000%

    No Known Activations