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. 0-CLT-HP
    4. 44251
    Prev
    Next
    INDEX
    Explanations

    Oxford

    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
    es
    -0.61
    i
    -0.48
    ratory
    -0.47
    y
    -0.47
    mata
    -0.46
     phi
    -0.46
    an
    -0.46
    Foreign
    -0.45
    อร
    -0.44
    er
    -0.43
    POSITIVE LOGITS
    ">//
    0.81
    __":
    
    0.75
    featureID
    0.73
    ValueStyle
    0.69
     récente
    0.69
    fjspx
    0.68
     générations
    0.68
    ContentAsync
    0.66
     contenir
    0.65
     Subsystem
    0.63
    Activations Density 0.067%

    No Known Activations