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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73874
    Prev
    Next
    INDEX
    Explanations

    Code/names

    np_max-act-logits · 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
    TintMode
    -0.72
     通販
    -0.62
    Ingestion
    -0.60
    enumi
    -0.60
     насељу
    -0.53
    StoryboardSegue
    -0.53
    toarele
    -0.52
     BorderRadius
    -0.52
    SBATCH
    -0.50
    didReceive
    -0.50
    POSITIVE LOGITS
    NewUrlParser
    0.55
    </thead>
    0.46
     Maak
    0.45
     Ess
    0.45
     ECL
    0.45
     Gibbon
    0.44
    ΩΝ
    0.43
     Shand
    0.43
     eventdata
    0.43
     General
    0.43
    Activations Density 0.000%

    No Known Activations