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. 1-CLT-HP
    4. 221
    Prev
    Next
    INDEX
    Explanations

    warming

    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
    NOPQRST
    -0.65
    fromnode
    -0.59
     viewDidLoad
    -0.57
     StatelessWidget
    -0.56
    +#+#
    -0.53
    coglie
    -0.53
     convertView
    -0.51
     lenker
    -0.50
    ulemon
    -0.50
    acco
    -0.49
    POSITIVE LOGITS
     الحره
    0.66
    IUrlHelper
    0.63
    ніципалі
    0.58
     ModelExpression
    0.52
     consultato
    0.52
    ="@+
    0.50
     Aplica
    0.50
     الوطنيه
    0.49
    ★★★★☆
    0.48
     ProtoMessage
    0.47
    Activations Density 0.126%

    No Known Activations