© 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. 0-CLT-HP
    7. 44231
    Prev
    Next
    INDEX
    Explanations

    Code and decorations

    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
    ORMAL
    -0.65
    theless
    -0.63
    genöss
    -0.62
     Мексичка
    -0.61
    collant
    -0.60
    ormal
    -0.59
    曖昧さ回避
    -0.59
    prite
    -0.59
    plash
    -0.57
    ffiche
    -0.57
    POSITIVE LOGITS
    o
    0.74
    er
    0.72
    en
    0.72
    y
    0.70
    es
    0.68
    e
    0.65
    a
    0.64
    i
    0.63
    s
    0.58
    ی
    0.57
    Activations Density 1.610%

    No Known Activations