© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93104
    Prev
    Next
    INDEX
    Explanations

    will

    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
     Theſe
    -0.64
    ⓧ
    -0.59
     pinulongan
    -0.57
     فريبيس
    -0.56
     للمعارف
    -0.55
     Jefus
    -0.54
     tartalomajánló
    -0.54
    Sucesor
    -0.54
    viewDidLoad
    -0.52
    PreAuthorize
    -0.50
    POSITIVE LOGITS
     be
    0.81
    StoryboardSegue
    0.67
     beru
    0.63
     appear
    0.61
     INCLUDE
    0.60
    look
    0.59
     talk
    0.59
     seem
    0.59
     Appear
    0.59
     address
    0.58
    Activations Density 0.001%

    No Known Activations