© 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. 1079
    Prev
    Next
    INDEX
    Explanations

    edal

    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
     myſelf
    -0.94
     auffi
    -0.93
     Monfieur
    -0.91
     Jefus
    -0.84
     Reſ
    -0.83
    ⓧ
    -0.81
     Diſ
    -0.80
    SOUNDBITE
    -0.78
     Houſe
    -0.77
    aarrggbb
    -0.76
    POSITIVE LOGITS
    —
    0.57
     of
    0.54
     —
    0.52
    tigs
    0.51
     private
    0.50
     thành
    0.50
     L
    0.48
     confund
    0.48
     
    0.48
    iny
    0.46
    Activations Density 0.132%

    No Known Activations