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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74235
    Prev
    Next
    INDEX
    Explanations

    do

    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
    Brainz
    -0.56
    ziej
    -0.47
     aient
    -0.44
     gearbeitet
    -0.43
     soient
    -0.43
    cuadro
    -0.42
    did
    -0.41
    Be
    -0.41
    دانشنامهٔ
    -0.40
    BindView
    -0.40
    POSITIVE LOGITS
    AnchorStyles
    0.77
     care
    0.73
     report
    0.66
     ویکی‌پدیا
    0.66
     do
    0.65
     encounter
    0.63
     muster
    0.62
     Roskov
    0.61
     support
    0.60
     mention
    0.60
    Activations Density 0.013%

    No Known Activations