© 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. 4-CLT-HP
    7. 4402
    Prev
    Next
    INDEX
    Explanations

    encryption

    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
    twimg
    -0.57
    <bos>
    -0.57
     SUDOC
    -0.54
    ьаж
    -0.54
    DockStyle
    -0.52
     autorytatywna
    -0.52
    SequentialGroup
    -0.52
    Чыганаклар
    -0.50
     surla
    -0.49
     تضيفلها
    -0.48
    POSITIVE LOGITS
    ômetro
    0.57
     dispensation
    0.57
    — 
    0.56
    oficina
    0.56
     /\.
    0.56
    derung
    0.55
    haviour
    0.55
    doing
    0.55
     mandatario
    0.55
    versiti
    0.54
    Activations Density 0.001%

    No Known Activations