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. 74423
    Prev
    Next
    INDEX
    Explanations

    technical context

    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
    hoga
    -0.65
     AssemblyVersion
    -0.63
     ComVisible
    -0.62
    AndEndTag
    -0.61
    +#+#
    -0.59
     <<<<<<<<<<<<<<
    -0.59
     تضيفلها
    -0.57
    dymyr
    -0.54
    CopyWith
    -0.54
    fxml
    -0.51
    POSITIVE LOGITS
     lenker
    0.65
     loom
    0.51
    Referencies
    0.50
     VIDEOTAPE
    0.50
    otyping
    0.48
     يتيمه
    0.47
    IUrlHelper
    0.47
     reaper
    0.47
     stitching
    0.46
     Loom
    0.46
    Activations Density 0.000%

    No Known Activations