© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1021
    Prev
    Next
    INDEX
    Explanations

    entially

    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
    ally
    -0.58
    Bard
    -0.53
     thesis
    -0.50
    ning
    -0.50
    httphttps
    -0.49
    стави
    -0.48
    CORD
    -0.48
    izing
    -0.48
     nati
    -0.47
     siir
    -0.46
    POSITIVE LOGITS
    findpost
    0.88
    XmlAccessType
    0.82
    enumii
    0.82
    setVerticalGroup
    0.73
    Personendaten
    0.72
    
    0.68
    يميديا
    0.67
     تضيفلها
    0.66
    kloped
    0.66
    JsonHelper
    0.66
    Activations Density 0.730%

    No Known Activations