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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96017
    Prev
    Next
    INDEX
    Explanations

    time and conditions

    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
     mögen
    -0.58
    them
    -0.52
     아니
    -0.52
     ktorá
    -0.51
     kirjo
    -0.50
    Completely
    -0.50
    Totally
    -0.50
    "]);
    -0.48
     They
    -0.47
    Abitanti
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.66
     you
    0.63
    IActionResult
    0.59
    neté
    0.59
     while
    0.57
     instead
    0.57
     Roskov
    0.56
     each
    0.54
     whilst
    0.54
    mybatisplus
    0.54
    Activations Density 0.002%

    No Known Activations