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. 74370
    Prev
    Next
    INDEX
    Explanations

    vascular

    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
    govine
    -0.47
     tempio
    -0.43
    dAtA
    -0.42
    ða
    -0.42
    TestBed
    -0.42
    ティア
    -0.41
     vVar
    -0.41
    ViewById
    -0.41
    cabulary
    -0.41
    lapsingToolbar
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.65
    RectangleBorder
    0.64
     propOrder
    0.61
    InjectAttribute
    0.60
     Wikispecies
    0.56
    rungsseite
    0.56
     referenties
    0.54
    XmlEnum
    0.52
    ]-->
    0.52
    ArgsConstructor
    0.52
    Activations Density 0.014%

    No Known Activations