© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    directions

    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
     Monfieur
    -0.96
     myſelf
    -0.93
     Efq
    -0.86
     Jefus
    -0.85
     themſelves
    -0.84
     itſelf
    -0.82
     whoſe
    -0.80
     avoient
    -0.80
     himſelf
    -0.79
    DebuggerNonUser
    -0.79
    POSITIVE LOGITS
    most
    0.78
     most
    0.65
    -
    0.59
    MOST
    0.53
    vag
    0.48
     Most
    0.47
     bu
    0.46
     b
    0.46
     end
    0.46
    Most
    0.46
    Activations Density 0.016%

    No Known Activations