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. 0-CLT-HP
    4. 91762
    Prev
    Next
    INDEX
    Explanations

    groupings

    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
    #+#
    -0.94
    Sucesor
    -0.92
     Мексичка
    -0.89
    DockStyle
    -0.89
     financières
    -0.81
    ieteur
    -0.79
     végétale
    -0.77
     leprosy
    -0.76
     caste
    -0.75
     ethnicity
    -0.74
    POSITIVE LOGITS
    ary
    0.70
    ists
    0.59
     hall
    0.58
    able
    0.55
    ably
    0.53
     Hall
    0.52
    ament
    0.52
    iert
    0.52
    ally
    0.50
    uality
    0.50
    Activations Density 0.200%

    No Known Activations