© 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. 980
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    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
     itſelf
    -1.13
     themſelves
    -1.06
     myſelf
    -0.99
    ſelves
    -0.99
     tartalomajánló
    -0.91
     purpoſe
    -0.88
    ſelf
    -0.87
     pleaſure
    -0.85
     <<<<<<<<<<<<<<
    -0.84
     ſtate
    -0.84
    POSITIVE LOGITS
     is
    0.61
     has
    0.48
    //
    0.47
    begin
    0.46
    SwingConstants
    0.44
    .
    0.43
     able
    0.43
     feeling
    0.43
     starts
    0.42
     u
    0.42
    Activations Density 0.059%

    No Known Activations