© 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. 97901
    Prev
    Next
    INDEX
    Explanations

    of

    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
    CodedInputStream
    -0.58
     viewDidLoad
    -0.58
    InstanceState
    -0.57
    Snoo
    -0.54
     initComponents
    -0.53
    expandindo
    -0.53
    LookAnd
    -0.53
     sutures
    -0.52
     MonoBehaviour
    -0.51
     epithe
    -0.51
    POSITIVE LOGITS
     decision
    0.64
     analysis
    0.59
    Explicación
    0.53
     life
    0.50
    álise
    0.49
     décision
    0.48
     tekem
    0.48
    analysis
    0.48
     writing
    0.48
     thinking
    0.48
    Activations Density 0.004%

    No Known Activations