© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96113
    Prev
    Next
    INDEX
    Explanations

    the

    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
    tvguidetime
    -0.85
     Forumite
    -0.85
    ^(@)
    -0.78
     ComVisible
    -0.77
    ViewImports
    -0.77
     disambiguazione
    -0.77
     Мексичка
    -0.76
     ―――――
    -0.76
    >\<^
    -0.76
     betweenstory
    -0.75
    POSITIVE LOGITS
     and
    0.63
     as
    0.49
    and
    0.45
    ↵
    0.43
    b
    0.42
    p
    0.41
     supérieures
    0.40
    AddTagHelper
    0.40
    id
    0.40
     This
    0.39
    Activations Density 0.009%

    No Known Activations