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. 0-CLT-HP
    4. 44825
    Prev
    Next
    INDEX
    Explanations

    products and services

    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
     draft
    -0.47
     turban
    -0.47
     profitable
    -0.46
     insured
    -0.46
     moschino
    -0.46
     gardeners
    -0.45
    solete
    -0.45
     ſmall
    -0.45
    bestimm
    -0.45
     rabbi
    -0.44
    POSITIVE LOGITS
    <bos>
    1.38
    ⓧ
    1.02
     esternos
    0.89
    tagHelperRunner
    0.85
     Paglinawan
    0.80
    principalColumn
    0.71
    SharedDtor
    0.71
    AccessorTable
    0.69
    CodedInputStream
    0.68
     nahilalakip
    0.68
    Activations Density 0.228%

    No Known Activations