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. 1-CLT-HP
    4. 12641
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · 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
    SuccessListener
    -0.62
    ArgsConstructor
    -0.60
     Cull
    -0.60
     PhpStorm
    -0.52
    "/",
    -0.52
     jsPsych
    -0.51
     Cowley
    -0.50
     IBOutlet
    -0.49
    IntoConstraints
    -0.48
     EconPapers
    -0.47
    POSITIVE LOGITS
    NewReader
    0.59
     تانيه
    0.56
    uronic
    0.55
    ellee
    0.48
    PreferredItem
    0.48
    urence
    0.48
    fira
    0.47
    vět
    0.47
    mirror
    0.47
    \{\\
    0.47
    Activations Density 0.053%

    No Known Activations