© 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. 0-CLT-HP
    7. 93521
    Prev
    Next
    INDEX
    Explanations

    patents and technical descriptions

    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
    onAttach
    -0.73
     ta
    -0.55
     composite
    -0.50
     EventArgs
    -0.49
    IsPostBack
    -0.48
     lu
    -0.47
     po
    -0.46
     Composite
    -0.45
    Eloquent
    -0.45
     cap
    -0.45
    POSITIVE LOGITS
     purpoſe
    1.03
     Jefus
    0.92
     ſta
    0.92
     itſelf
    0.90
     Philist
    0.89
     myſelf
    0.87
     ſtate
    0.85
     ſche
    0.85
     Chriſt
    0.84
     Majefty
    0.84
    Activations Density 0.081%

    No Known Activations