© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45140
    Prev
    Next
    INDEX
    Explanations

    measurement and improvement

    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
     sur
    -0.57
     la
    -0.55
     supporters
    -0.54
     se
    -0.52
     C
    -0.52
     c
    -0.51
     p
    -0.51
     He
    -0.51
    bele
    -0.51
     supporter
    -0.50
    POSITIVE LOGITS
     myſelf
    1.31
     purpoſe
    1.20
     houſe
    1.19
     itſelf
    1.15
     Jefus
    1.13
     pleaſure
    1.12
     Reſ
    1.10
     Monfieur
    1.09
     themſelves
    1.08
     faſt
    1.08
    Activations Density 0.270%

    No Known Activations