© 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. 0-CLT-HP
    7. 38989
    Prev
    Next
    INDEX
    Explanations

    Malcolm

    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
     Malcolm
    -2.05
    Malcolm
    -1.78
     Infórmanos
    -0.87
     nahilalakip
    -0.79
     Spisak
    -0.77
     $_"
    -0.77
     ivelany
    -0.77
     purpoſe
    -0.76
     Monfieur
    -0.75
     ―――――
    -0.74
    POSITIVE LOGITS
     “
    0.53
     Ter
    0.49
     Dec
    0.48
    ="@+
    0.48
    merkungen
    0.48
    står
    0.47
     Ger
    0.45
     Fer
    0.45
    носить
    0.44
     J
    0.43
    Activations Density 0.125%

    No Known Activations