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. 39728
    Prev
    Next
    INDEX
    Explanations

    trans

    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
     sub
    -1.09
     Sub
    -1.01
     Group
    -0.84
     
    -0.81
     in
    -0.80
     L
    -0.79
     W
    -0.77
     G
    -0.76
     B
    -0.76
     P
    -0.75
    POSITIVE LOGITS
     Monfieur
    1.55
     itſelf
    1.53
     myſelf
    1.52
     Efq
    1.48
     Theſe
    1.43
     houſe
    1.39
     themſelves
    1.38
     Anſ
    1.38
     faſt
    1.37
    ſelves
    1.36
    Activations Density 0.275%

    No Known Activations