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. 74389
    Prev
    Next
    INDEX
    Explanations

    Long

    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
    Personendaten
    -0.99
    AddTagHelper
    -0.94
    enumi
    -0.76
     jLabel
    -0.71
     AssemblyProduct
    -0.69
    __(/*!
    -0.69
    styleType
    -0.68
     gynhyrchwyd
    -0.68
     beginnetje
    -0.67
     يتيمه
    -0.66
    POSITIVE LOGITS
    AttributeSet
    0.43
    ber
    0.42
    ACC
    0.42
    Als
    0.40
     ber
    0.40
    bes
    0.40
     Co
    0.39
    antd
    0.39
     almas
    0.38
     th
    0.37
    Activations Density 0.094%

    No Known Activations