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. 74292
    Prev
    Next
    INDEX
    Explanations

    code/files

    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
    lwjgl
    -0.56
    RY
    -0.56
    хии
    -0.52
     Cho
    -0.50
     Cor
    -0.50
    ry
    -0.48
    hdys
    -0.47
     T
    -0.45
    chro
    -0.45
    hasOwnProperty
    -0.44
    POSITIVE LOGITS
    HtmlAttribute
    0.72
    AndEndTag
    0.66
     Audiodateien
    0.65
     estekak
    0.63
    각주
    0.58
     ems
    0.58
    StoreMessageInfo
    0.57
     Профиль
    0.56
    Palmar
    0.56
     OGS
    0.55
    Activations Density 0.001%

    No Known Activations