© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 361
    Prev
    Next
    INDEX
    Explanations

    scroll, update, append

    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
    ExtendWith
    -0.59
     Audiodateien
    -0.55
    ^(@)
    -0.53
    ˏ
    -0.52
    Holo
    -0.50
    gdx
    -0.49
    期刊论文
    -0.49
    bonucleic
    -0.48
    ագրություններ
    -0.47
    oleic
    -0.47
    POSITIVE LOGITS
     the
    0.77
    <bos>
    0.54
     a
    0.52
     makl
    0.52
    MessageOf
    0.50
    ]='\
    0.49
     fieldNum
    0.49
     Мексичка
    0.49
     ویکی‌پدی
    0.49
    sizeCache
    0.48
    Activations Density 0.044%

    No Known Activations