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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74473
    Prev
    Next
    INDEX
    Explanations

    Rochester

    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
    OGND
    -0.69
     ostavi
    -0.65
     esterni
    -0.57
    icals
    -0.53
     CBT
    -0.49
    cesis
    -0.48
    webElementXpaths
    -0.47
    CROSSTALK
    -0.47
     canais
    -0.47
     fiscale
    -0.47
    POSITIVE LOGITS
    UrlResolution
    0.63
    彿
    0.54
    DrawerLayout
    0.47
     StatelessWidget
    0.46
     CreateTagHelper
    0.45
    gera
    0.44
    twimg
    0.43
     handleChange
    0.43
    ViewFeatures
    0.43
     noqa
    0.43
    Activations Density 0.007%

    No Known Activations