© 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. 5-CLT-HP
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    named

    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
     in
    -1.10
     as
    -1.02
    ,
    -0.97
     after
    -0.96
     by
    -0.93
     on
    -0.92
     at
    -0.88
    :
    -0.87
     for
    -0.85
    .
    -0.82
    POSITIVE LOGITS
     nahilalakip
    1.05
    Datuak
    1.05
     myſelf
    1.03
     متعلقه
    0.99
     itſelf
    0.98
     whoſe
    0.96
     Мексичка
    0.93
    OGND
    0.92
    دانشنامهٔ
    0.91
     насељу
    0.91
    Activations Density 0.001%

    No Known Activations